Peng Gao

Renrui Zhang, Jiaming Han, Chris Liu et al. · stanford

We present LLaMA-Adapter, a lightweight adaption method to efficiently fine-tune LLaMA into an instruction-following model. Using 52K self-instruct demonstrations, LLaMA-Adapter only introduces 1.2M learnable parameters upon the frozen LLaMA 7B model, and costs less than one hour for fine-tuning on 8 A100 GPUs. Specifically, we adopt a set of learnable adaption prompts, and prepend them to the word tokens at higher transformer layers. Then, a zero-initialized attention mechanism with zero gating is proposed, which adaptively injects the new instructional cues into LLaMA, while effectively preserves its pre-trained knowledge. With our efficient training, LLaMA-Adapter can generate high-quality responses, comparable to Alpaca with fully fine-tuned 7B parameters. Besides language commands, our approach can be simply extended to multi-modal instructions for learning image-conditioned LLaMA model, which achieves superior reasoning performance on ScienceQA and COCO Caption benchmarks. Furthermore, we also evaluate the zero-initialized attention mechanism for fine-tuning other pre-trained models (ViT, RoBERTa) on traditional vision and language tasks, demonstrating the superior generalization capacity of our approach. Code is released at https://github.com/OpenGVLab/LLaMA-Adapter.

Peng Gao, Jiaming Han, Renrui Zhang et al. · berkeley, stanford

How to efficiently transform large language models (LLMs) into instruction followers is recently a popular research direction, while training LLM for multi-modal reasoning remains less explored. Although the recent LLaMA-Adapter demonstrates the potential to handle visual inputs with LLMs, it still cannot generalize well to open-ended visual instructions and lags behind GPT-4. In this paper, we present LLaMA-Adapter V2, a parameter-efficient visual instruction model. Specifically, we first augment LLaMA-Adapter by unlocking more learnable parameters (e.g., norm, bias and scale), which distribute the instruction-following ability across the entire LLaMA model besides adapters. Secondly, we propose an early fusion strategy to feed visual tokens only into the early LLM layers, contributing to better visual knowledge incorporation. Thirdly, a joint training paradigm of image-text pairs and instruction-following data is introduced by optimizing disjoint groups of learnable parameters. This strategy effectively alleviates the interference between the two tasks of image-text alignment and instruction following and achieves strong multi-modal reasoning with only a small-scale image-text and instruction dataset. During inference, we incorporate additional expert models (e.g. captioning/OCR systems) into LLaMA-Adapter to further enhance its image understanding capability without incurring training costs. Compared to the original LLaMA-Adapter, our LLaMA-Adapter V2 can perform open-ended multi-modal instructions by merely introducing 14M parameters over LLaMA. The newly designed framework also exhibits stronger language-only instruction-following capabilities and even excels in chat interactions. Our code and models are available at https://github.com/ZrrSkywalker/LLaMA-Adapter.

Ziteng Cui, Kunchang Li, Lin Gu et al. · tencent-ai

Challenging illumination conditions (low-light, under-exposure and over-exposure) in the real world not only cast an unpleasant visual appearance but also taint the computer vision tasks. After camera captures the raw-RGB data, it renders standard sRGB images with image signal processor (ISP). By decomposing ISP pipeline into local and global image components, we propose a lightweight fast Illumination Adaptive Transformer (IAT) to restore the normal lit sRGB image from either low-light or under/over-exposure conditions. Specifically, IAT uses attention queries to represent and adjust the ISP-related parameters such as colour correction, gamma correction. With only ~90k parameters and ~0.004s processing speed, our IAT consistently achieves superior performance over SOTA on the current benchmark low-light enhancement and exposure correction datasets. Competitive experimental performance also demonstrates that our IAT significantly enhances object detection and semantic segmentation tasks under various light conditions. Training code and pretrained model is available at https://github.com/cuiziteng/Illumination-Adaptive-Transformer.

Renrui Zhang, Zhang Wei, Rongyao Fang et al.

Contrastive Vision-Language Pre-training, known as CLIP, has provided a new paradigm for learning visual representations using large-scale image-text pairs. It shows impressive performance on downstream tasks by zero-shot knowledge transfer. To further enhance CLIP's adaption capability, existing methods proposed to fine-tune additional learnable modules, which significantly improves the few-shot performance but introduces extra training time and computational resources. In this paper, we propose a training-free adaption method for CLIP to conduct few-shot classification, termed as Tip-Adapter, which not only inherits the training-free advantage of zero-shot CLIP but also performs comparably to those training-required approaches. Tip-Adapter constructs the adapter via a key-value cache model from the few-shot training set, and updates the prior knowledge encoded in CLIP by feature retrieval. On top of that, the performance of Tip-Adapter can be further boosted to be state-of-the-art on ImageNet by fine-tuning the cache model for 10$\times$ fewer epochs than existing methods, which is both effective and efficient. We conduct extensive experiments of few-shot classification on 11 datasets to demonstrate the superiority of our proposed methods. Code is released at https://github.com/gaopengcuhk/Tip-Adapter.

Zhengkai Jiang, Yuxi Li, Ceyuan Yang et al. · tencent-ai

Unsupervised Domain Adaptation (UDA) aims to adapt the model trained on the labeled source domain to an unlabeled target domain. In this paper, we present Prototypical Contrast Adaptation (ProCA), a simple and efficient contrastive learning method for unsupervised domain adaptive semantic segmentation. Previous domain adaptation methods merely consider the alignment of the intra-class representational distributions across various domains, while the inter-class structural relationship is insufficiently explored, resulting in the aligned representations on the target domain might not be as easily discriminated as done on the source domain anymore. Instead, ProCA incorporates inter-class information into class-wise prototypes, and adopts the class-centered distribution alignment for adaptation. By considering the same class prototypes as positives and other class prototypes as negatives to achieve class-centered distribution alignment, ProCA achieves state-of-the-art performance on classical domain adaptation tasks, {\em i.e., GTA5 $\to$ Cityscapes \text{and} SYNTHIA $\to$ Cityscapes}. Code is available at \href{https://github.com/jiangzhengkai/ProCA}{ProCA}

Renrui Zhang, Ziyu Guo, Rongyao Fang et al.

Masked Autoencoders (MAE) have shown great potentials in self-supervised pre-training for language and 2D image transformers. However, it still remains an open question on how to exploit masked autoencoding for learning 3D representations of irregular point clouds. In this paper, we propose Point-M2AE, a strong Multi-scale MAE pre-training framework for hierarchical self-supervised learning of 3D point clouds. Unlike the standard transformer in MAE, we modify the encoder and decoder into pyramid architectures to progressively model spatial geometries and capture both fine-grained and high-level semantics of 3D shapes. For the encoder that downsamples point tokens by stages, we design a multi-scale masking strategy to generate consistent visible regions across scales, and adopt a local spatial self-attention mechanism during fine-tuning to focus on neighboring patterns. By multi-scale token propagation, the lightweight decoder gradually upsamples point tokens with complementary skip connections from the encoder, which further promotes the reconstruction from a global-to-local perspective. Extensive experiments demonstrate the state-of-the-art performance of Point-M2AE for 3D representation learning. With a frozen encoder after pre-training, Point-M2AE achieves 92.9% accuracy for linear SVM on ModelNet40, even surpassing some fully trained methods. By fine-tuning on downstream tasks, Point-M2AE achieves 86.43% accuracy on ScanObjectNN, +3.36% to the second-best, and largely benefits the few-shot classification, part segmentation and 3D object detection with the hierarchical pre-training scheme. Code is available at https://github.com/ZrrSkywalker/Point-M2AE.

Renrui Zhang, Xiangfei Hu, Bohao Li et al.

Visual recognition in low-data regimes requires deep neural networks to learn generalized representations from limited training samples. Recently, CLIP-based methods have shown promising few-shot performance benefited from the contrastive language-image pre-training. We then question, if the more diverse pre-training knowledge can be cascaded to further assist few-shot representation learning. In this paper, we propose CaFo, a Cascade of Foundation models that incorporates diverse prior knowledge of various pre-training paradigms for better few-shot learning. Our CaFo incorporates CLIP's language-contrastive knowledge, DINO's vision-contrastive knowledge, DALL-E's vision-generative knowledge, and GPT-3's language-generative knowledge. Specifically, CaFo works by 'Prompt, Generate, then Cache'. Firstly, we leverage GPT-3 to produce textual inputs for prompting CLIP with rich downstream linguistic semantics. Then, we generate synthetic images via DALL-E to expand the few-shot training data without any manpower. At last, we introduce a learnable cache model to adaptively blend the predictions from CLIP and DINO. By such collaboration, CaFo can fully unleash the potential of different pre-training methods and unify them to perform state-of-the-art for few-shot classification. Code is available at https://github.com/ZrrSkywalker/CaFo.

Renrui Zhang, Liuhui Wang, Yu Qiao et al.

Pre-training by numerous image data has become de-facto for robust 2D representations. In contrast, due to the expensive data acquisition and annotation, a paucity of large-scale 3D datasets severely hinders the learning for high-quality 3D features. In this paper, we propose an alternative to obtain superior 3D representations from 2D pre-trained models via Image-to-Point Masked Autoencoders, named as I2P-MAE. By self-supervised pre-training, we leverage the well learned 2D knowledge to guide 3D masked autoencoding, which reconstructs the masked point tokens with an encoder-decoder architecture. Specifically, we first utilize off-the-shelf 2D models to extract the multi-view visual features of the input point cloud, and then conduct two types of image-to-point learning schemes on top. For one, we introduce a 2D-guided masking strategy that maintains semantically important point tokens to be visible for the encoder. Compared to random masking, the network can better concentrate on significant 3D structures and recover the masked tokens from key spatial cues. For another, we enforce these visible tokens to reconstruct the corresponding multi-view 2D features after the decoder. This enables the network to effectively inherit high-level 2D semantics learned from rich image data for discriminative 3D modeling. Aided by our image-to-point pre-training, the frozen I2P-MAE, without any fine-tuning, achieves 93.4% accuracy for linear SVM on ModelNet40, competitive to the fully trained results of existing methods. By further fine-tuning on on ScanObjectNN's hardest split, I2P-MAE attains the state-of-the-art 90.11% accuracy, +3.68% to the second-best, demonstrating superior transferable capacity. Code will be available at https://github.com/ZrrSkywalker/I2P-MAE.

Renrui Zhang, Han Qiu, Tai Wang et al.

Monocular 3D object detection has long been a challenging task in autonomous driving. Most existing methods follow conventional 2D detectors to first localize object centers, and then predict 3D attributes by neighboring features. However, only using local visual features is insufficient to understand the scene-level 3D spatial structures and ignores the long-range inter-object depth relations. In this paper, we introduce the first DETR framework for Monocular DEtection with a depth-guided TRansformer, named MonoDETR. We modify the vanilla transformer to be depth-aware and guide the whole detection process by contextual depth cues. Specifically, concurrent to the visual encoder that captures object appearances, we introduce to predict a foreground depth map, and specialize a depth encoder to extract non-local depth embeddings. Then, we formulate 3D object candidates as learnable queries and propose a depth-guided decoder to conduct object-scene depth interactions. In this way, each object query estimates its 3D attributes adaptively from the depth-guided regions on the image and is no longer constrained to local visual features. On KITTI benchmark with monocular images as input, MonoDETR achieves state-of-the-art performance and requires no extra dense depth annotations. Besides, our depth-guided modules can also be plug-and-play to enhance multi-view 3D object detectors on nuScenes dataset, demonstrating our superior generalization capacity. Code is available at https://github.com/ZrrSkywalker/MonoDETR.

Peng Gao, Teli Ma, Hongsheng Li et al.

Vision Transformers (ViT) become widely-adopted architectures for various vision tasks. Masked auto-encoding for feature pretraining and multi-scale hybrid convolution-transformer architectures can further unleash the potentials of ViT, leading to state-of-the-art performances on image classification, detection and semantic segmentation. In this paper, our ConvMAE framework demonstrates that multi-scale hybrid convolution-transformer can learn more discriminative representations via the mask auto-encoding scheme. However, directly using the original masking strategy leads to the heavy computational cost and pretraining-finetuning discrepancy. To tackle the issue, we adopt the masked convolution to prevent information leakage in the convolution blocks. A simple block-wise masking strategy is proposed to ensure computational efficiency. We also propose to more directly supervise the multi-scale features of the encoder to boost multi-scale features. Based on our pretrained ConvMAE models, ConvMAE-Base improves ImageNet-1K finetuning accuracy by 1.4% compared with MAE-Base. On object detection, ConvMAE-Base finetuned for only 25 epochs surpasses MAE-Base fined-tuned for 100 epochs by 2.9% box AP and 2.2% mask AP respectively. Code and pretrained models are available at https://github.com/Alpha-VL/ConvMAE.

Ziyi Lin, Shijie Geng, Renrui Zhang et al.

Video recognition has been dominated by the end-to-end learning paradigm -- first initializing a video recognition model with weights of a pretrained image model and then conducting end-to-end training on videos. This enables the video network to benefit from the pretrained image model. However, this requires substantial computation and memory resources for finetuning on videos and the alternative of directly using pretrained image features without finetuning the image backbone leads to subpar results. Fortunately, recent advances in Contrastive Vision-Language Pre-training (CLIP) pave the way for a new route for visual recognition tasks. Pretrained on large open-vocabulary image-text pair data, these models learn powerful visual representations with rich semantics. In this paper, we present Efficient Video Learning (EVL) -- an efficient framework for directly training high-quality video recognition models with frozen CLIP features. Specifically, we employ a lightweight Transformer decoder and learn a query token to dynamically collect frame-level spatial features from the CLIP image encoder. Furthermore, we adopt a local temporal module in each decoder layer to discover temporal clues from adjacent frames and their attention maps. We show that despite being efficient to train with a frozen backbone, our models learn high quality video representations on a variety of video recognition datasets. Code is available at https://github.com/OpenGVLab/efficient-video-recognition.

Renrui Zhang, Liuhui Wang, Ziyu Guo et al.

We present a Non-parametric Network for 3D point cloud analysis, Point-NN, which consists of purely non-learnable components: farthest point sampling (FPS), k-nearest neighbors (k-NN), and pooling operations, with trigonometric functions. Surprisingly, it performs well on various 3D tasks, requiring no parameters or training, and even surpasses existing fully trained models. Starting from this basic non-parametric model, we propose two extensions. First, Point-NN can serve as a base architectural framework to construct Parametric Networks by simply inserting linear layers on top. Given the superior non-parametric foundation, the derived Point-PN exhibits a high performance-efficiency trade-off with only a few learnable parameters. Second, Point-NN can be regarded as a plug-and-play module for the already trained 3D models during inference. Point-NN captures the complementary geometric knowledge and enhances existing methods for different 3D benchmarks without re-training. We hope our work may cast a light on the community for understanding 3D point clouds with non-parametric methods. Code is available at https://github.com/ZrrSkywalker/Point-NN.

Hongwei Xue, Peng Gao, Hongyang Li et al.

Masked Autoencoders (MAE) have been prevailing paradigms for large-scale vision representation pre-training. By reconstructing masked image patches from a small portion of visible image regions, MAE forces the model to infer semantic correlation within an image. Recently, some approaches apply semantic-rich teacher models to extract image features as the reconstruction target, leading to better performance. However, unlike the low-level features such as pixel values, we argue the features extracted by powerful teacher models already encode rich semantic correlation across regions in an intact image.This raises one question: is reconstruction necessary in Masked Image Modeling (MIM) with a teacher model? In this paper, we propose an efficient MIM paradigm named MaskAlign. MaskAlign simply learns the consistency of visible patch features extracted by the student model and intact image features extracted by the teacher model. To further advance the performance and tackle the problem of input inconsistency between the student and teacher model, we propose a Dynamic Alignment (DA) module to apply learnable alignment. Our experimental results demonstrate that masked modeling does not lose effectiveness even without reconstruction on masked regions. Combined with Dynamic Alignment, MaskAlign can achieve state-of-the-art performance with much higher efficiency. Code and models will be available at https://github.com/OpenPerceptionX/maskalign.

Yanjing Li, Sheng Xu, Baochang Zhang et al.

The large pre-trained vision transformers (ViTs) have demonstrated remarkable performance on various visual tasks, but suffer from expensive computational and memory cost problems when deployed on resource-constrained devices. Among the powerful compression approaches, quantization extremely reduces the computation and memory consumption by low-bit parameters and bit-wise operations. However, low-bit ViTs remain largely unexplored and usually suffer from a significant performance drop compared with the real-valued counterparts. In this work, through extensive empirical analysis, we first identify the bottleneck for severe performance drop comes from the information distortion of the low-bit quantized self-attention map. We then develop an information rectification module (IRM) and a distribution guided distillation (DGD) scheme for fully quantized vision transformers (Q-ViT) to effectively eliminate such distortion, leading to a fully quantized ViTs. We evaluate our methods on popular DeiT and Swin backbones. Extensive experimental results show that our method achieves a much better performance than the prior arts. For example, our Q-ViT can theoretically accelerates the ViT-S by 6.14x and achieves about 80.9% Top-1 accuracy, even surpassing the full-precision counterpart by 1.0% on ImageNet dataset. Our codes and models are attached on https://github.com/YanjingLi0202/Q-ViT

Peng Gao, Renrui Zhang, Rongyao Fang et al.

Masked Autoencoders (MAE) have been popular paradigms for large-scale vision representation pre-training. However, MAE solely reconstructs the low-level RGB signals after the decoder and lacks supervision upon high-level semantics for the encoder, thus suffering from sub-optimal learned representations and long pre-training epochs. To alleviate this, previous methods simply replace the pixel reconstruction targets of 75% masked tokens by encoded features from pre-trained image-image (DINO) or image-language (CLIP) contrastive learning. Different from those efforts, we propose to Mimic before Reconstruct for Masked Autoencoders, named as MR-MAE, which jointly learns high-level and low-level representations without interference during pre-training. For high-level semantics, MR-MAE employs a mimic loss over 25% visible tokens from the encoder to capture the pre-trained patterns encoded in CLIP and DINO. For low-level structures, we inherit the reconstruction loss in MAE to predict RGB pixel values for 75% masked tokens after the decoder. As MR-MAE applies high-level and low-level targets respectively at different partitions, the learning conflicts between them can be naturally overcome and contribute to superior visual representations for various downstream tasks. On ImageNet-1K, the MR-MAE base pre-trained for only 400 epochs achieves 85.8% top-1 accuracy after fine-tuning, surpassing the 1600-epoch MAE base by +2.2% and the previous state-of-the-art BEiT V2 base by +0.3%. Code and pre-trained models will be released at https://github.com/Alpha-VL/ConvMAE.

Sheng Xu, Yanjing Li, Teli Ma et al.

Binary neural networks (BNNs) have received ever-increasing popularity for their great capability of reducing storage burden as well as quickening inference time. However, there is a severe performance drop compared with real-valued networks, due to its intrinsic frequent weight oscillation during training. In this paper, we introduce a Resilient Binary Neural Network (ReBNN) to mitigate the frequent oscillation for better BNNs' training. We identify that the weight oscillation mainly stems from the non-parametric scaling factor. To address this issue, we propose to parameterize the scaling factor and introduce a weighted reconstruction loss to build an adaptive training objective. For the first time, we show that the weight oscillation is controlled by the balanced parameter attached to the reconstruction loss, which provides a theoretical foundation to parameterize it in back propagation. Based on this, we learn our ReBNN by calculating the balanced parameter based on its maximum magnitude, which can effectively mitigate the weight oscillation with a resilient training process. Extensive experiments are conducted upon various network models, such as ResNet and Faster-RCNN for computer vision, as well as BERT for natural language processing. The results demonstrate the overwhelming performance of our ReBNN over prior arts. For example, our ReBNN achieves 66.9% Top-1 accuracy with ResNet-18 backbone on the ImageNet dataset, surpassing existing state-of-the-arts by a significant margin. Our code is open-sourced at https://github.com/SteveTsui/ReBNN.

Sheng Xu, Yanjing Li, Bohan Zeng et al.

Knowledge distillation (KD) has been proven to be useful for training compact object detection models. However, we observe that KD is often effective when the teacher model and student counterpart share similar proposal information. This explains why existing KD methods are less effective for 1-bit detectors, caused by a significant information discrepancy between the real-valued teacher and the 1-bit student. This paper presents an Information Discrepancy-aware strategy (IDa-Det) to distill 1-bit detectors that can effectively eliminate information discrepancies and significantly reduce the performance gap between a 1-bit detector and its real-valued counterpart. We formulate the distillation process as a bi-level optimization formulation. At the inner level, we select the representative proposals with maximum information discrepancy. We then introduce a novel entropy distillation loss to reduce the disparity based on the selected proposals. Extensive experiments demonstrate IDa-Det's superiority over state-of-the-art 1-bit detectors and KD methods on both PASCAL VOC and COCO datasets. IDa-Det achieves a 76.9% mAP for a 1-bit Faster-RCNN with ResNet-18 backbone. Our code is open-sourced on https://github.com/SteveTsui/IDa-Det.

Sheng Xu, Yanjing Li, Tiancheng Wang et al.

Binary Neural Networks (BNNs) show great promise for real-world embedded devices. As one of the critical steps to achieve a powerful BNN, the scale factor calculation plays an essential role in reducing the performance gap to their real-valued counterparts. However, existing BNNs neglect the intrinsic bilinear relationship of real-valued weights and scale factors, resulting in a sub-optimal model caused by an insufficient training process. To address this issue, Recurrent Bilinear Optimization is proposed to improve the learning process of BNNs (RBONNs) by associating the intrinsic bilinear variables in the back propagation process. Our work is the first attempt to optimize BNNs from the bilinear perspective. Specifically, we employ a recurrent optimization and Density-ReLU to sequentially backtrack the sparse real-valued weight filters, which will be sufficiently trained and reach their performance limits based on a controllable learning process. We obtain robust RBONNs, which show impressive performance over state-of-the-art BNNs on various models and datasets. Particularly, on the task of object detection, RBONNs have great generalization performance. Our code is open-sourced on https://github.com/SteveTsui/RBONN .

Kexue Fu, Peng Gao, ShaoLei Liu et al.

Recently, the pre-training paradigm combining Transformer and masked language modeling has achieved tremendous success in NLP, images, and point clouds, such as BERT. However, directly extending BERT from NLP to point clouds requires training a fixed discrete Variational AutoEncoder (dVAE) before pre-training, which results in a complex two-stage method called Point-BERT. Inspired by BERT and MoCo, we propose POS-BERT, a one-stage BERT pre-training method for point clouds. Specifically, we use the mask patch modeling (MPM) task to perform point cloud pre-training, which aims to recover masked patches information under the supervision of the corresponding tokenizer output. Unlike Point-BERT, its tokenizer is extra-trained and frozen. We propose to use the dynamically updated momentum encoder as the tokenizer, which is updated and outputs the dynamic supervision signal along with the training process. Further, in order to learn high-level semantic representation, we combine contrastive learning to maximize the class token consistency between different transformation point clouds. Extensive experiments have demonstrated that POS-BERT can extract high-quality pre-training features and promote downstream tasks to improve performance. Using the pre-training model without any fine-tuning to extract features and train linear SVM on ModelNet40, POS-BERT achieves the state-of-the-art classification accuracy, which exceeds Point-BERT by 3.5\%. In addition, our approach has significantly improved many downstream tasks, such as fine-tuned classification, few-shot classification, part segmentation. The code and trained-models will be available at: \url{https://github.com/fukexue/POS-BERT}.

Xiangyang Zhu, Renrui Zhang, Bowei He et al.

Large-scale pre-trained models have shown promising open-world performance for both vision and language tasks. However, their transferred capacity on 3D point clouds is still limited and only constrained to the classification task. In this paper, we first collaborate CLIP and GPT to be a unified 3D open-world learner, named as PointCLIP V2, which fully unleashes their potential for zero-shot 3D classification, segmentation, and detection. To better align 3D data with the pre-trained language knowledge, PointCLIP V2 contains two key designs. For the visual end, we prompt CLIP via a shape projection module to generate more realistic depth maps, narrowing the domain gap between projected point clouds with natural images. For the textual end, we prompt the GPT model to generate 3D-specific text as the input of CLIP's textual encoder. Without any training in 3D domains, our approach significantly surpasses PointCLIP by +42.90%, +40.44%, and +28.75% accuracy on three datasets for zero-shot 3D classification. On top of that, V2 can be extended to few-shot 3D classification, zero-shot 3D part segmentation, and 3D object detection in a simple manner, demonstrating our generalization ability for unified 3D open-world learning.

Xiangyang Zhu, Renrui Zhang, Bowei He et al.

The popularity of Contrastive Language-Image Pre-training (CLIP) has propelled its application to diverse downstream vision tasks. To improve its capacity on downstream tasks, few-shot learning has become a widely-adopted technique. However, existing methods either exhibit limited performance or suffer from excessive learnable parameters. In this paper, we propose APE, an Adaptive Prior rEfinement method for CLIP's pre-trained knowledge, which achieves superior accuracy with high computational efficiency. Via a prior refinement module, we analyze the inter-class disparity in the downstream data and decouple the domain-specific knowledge from the CLIP-extracted cache model. On top of that, we introduce two model variants, a training-free APE and a training-required APE-T. We explore the trilateral affinities between the test image, prior cache model, and textual representations, and only enable a lightweight category-residual module to be trained. For the average accuracy over 11 benchmarks, both APE and APE-T attain state-of-the-art and respectively outperform the second-best by +1.59% and +1.99% under 16 shots with x30 less learnable parameters.

Renrui Zhang, Bohao Li, Wei Zhang et al.

Few-shot classification requires deep neural networks to learn generalized representations only from limited training images, which is challenging but significant in low-data regimes. Recently, CLIP-based methods have shown promising few-shot performance benefited from the contrastive language-image pre-training. Based on this point, we question if the large-scale pre-training can alleviate the few-shot data deficiency and also assist the representation learning by the pre-learned knowledge. In this paper, we propose CoMo, a Collaboration of pre-trained Models that incorporates diverse prior knowledge from various pre-training paradigms for better few-shot learning. Our CoMo includes: CLIP's language-contrastive knowledge, DINO's vision-contrastive knowledge, and DALL-E's language-generative knowledge. Specifically, CoMo works in two aspects: few-shot data expansion and diverse knowledge ensemble. For one, we generate synthetic images via zero-shot DALL-E to enrich the few-shot training data without any manpower. For the other, we introduce a learnable Multi-Knowledge Adapter (MK-Adapter) to adaptively blend the predictions from CLIP and DINO. By such collaboration, CoMo can fully unleash the potential of different pre-training methods and unify them to perform state-of-the-art for few-shot classification. We conduct extensive experiments on 11 datasets to demonstrate the superiority and generalization ability of our approach.

Tong Zhang, Peng Gao, Hao Dong et al.

Currently, under supervised learning, a model pretrained by a large-scale nature scene dataset and then fine-tuned on a few specific task labeling data is the paradigm that has dominated the knowledge transfer learning. It has reached the status of consensus solution for task-aware model training in remote sensing domain (RSD). Unfortunately, due to different categories of imaging data and stiff challenges of data annotation, there is not a large enough and uniform remote sensing dataset to support large-scale pretraining in RSD. Moreover, pretraining models on large-scale nature scene datasets by supervised learning and then directly fine-tuning on diverse downstream tasks seems to be a crude method, which is easily affected by inevitable labeling noise, severe domain gaps and task-aware discrepancies. Thus, in this paper, considering the self-supervised pretraining and powerful vision transformer (ViT) architecture, a concise and effective knowledge transfer learning strategy called ConSecutive PreTraining (CSPT) is proposed based on the idea of not stopping pretraining in natural language processing (NLP), which can gradually bridge the domain gap and transfer knowledge from the nature scene domain to the RSD. The proposed CSPT also can release the huge potential of unlabeled data for task-aware model training. Finally, extensive experiments are carried out on twelve datasets in RSD involving three types of downstream tasks (e.g., scene classification, object detection and land cover classification) and two types of imaging data (e.g., optical and SAR). The results show that by utilizing the proposed CSPT for task-aware model training, almost all downstream tasks in RSD can outperform the previous method of supervised pretraining-then-fine-tuning and even surpass the state-of-the-art (SOTA) performance without any expensive labeling consumption and careful model design.

Xiaorui Wang, Jun Wang, Xin Tang et al.

Filter pruning is widely adopted to compress and accelerate the Convolutional Neural Networks (CNNs), but most previous works ignore the relationship between filters and channels in different layers. Processing each layer independently fails to utilize the collaborative relationship across layers. In this paper, we intuitively propose a novel pruning method by explicitly leveraging the Filters Similarity in Consecutive Layers (FSCL). FSCL compresses models by pruning filters whose corresponding features are more worthless in the model. The extensive experiments demonstrate the effectiveness of FSCL, and it yields remarkable improvement over state-of-the-art on accuracy, FLOPs and parameter reduction on several benchmark models and datasets.

Changyu Hou, Jun Wang, Yixuan Qiao et al.

Large scale pre-training models have been widely used in named entity recognition (NER) tasks. However, model ensemble through parameter averaging or voting can not give full play to the differentiation advantages of different models, especially in the open domain. This paper describes our NER system in the SemEval 2022 task11: MultiCoNER. We proposed an effective system to adaptively ensemble pre-trained language models by a Transformer layer. By assigning different weights to each model for different inputs, we adopted the Transformer layer to integrate the advantages of diverse models effectively. Experimental results show that our method achieves superior performances in Farsi and Dutch.

Yixuan Qiao, Shanshan Zhao, Jun Wang et al.

This paper describes the PASH participation in TREC 2021 Deep Learning Track. In the recall stage, we adopt a scheme combining sparse and dense retrieval method. In the multi-stage ranking phase, point-wise and pair-wise ranking strategies are used one after another based on model continual pre-trained on general knowledge and document-level data. Compared to TREC 2020 Deep Learning Track, we have additionally introduced the generative model T5 to further enhance the performance.

Xin Li, Siyuan Huang, Qiaojun Yu et al.

Automating garment manipulation poses a significant challenge for assistive robotics due to the diverse and deformable nature of garments. Traditional approaches typically require separate models for each garment type, which limits scalability and adaptability. In contrast, this paper presents a unified approach using vision-language models (VLMs) to improve keypoint prediction across various garment categories. By interpreting both visual and semantic information, our model enables robots to manage different garment states with a single model. We created a large-scale synthetic dataset using advanced simulation techniques, allowing scalable training without extensive real-world data. Experimental results indicate that the VLM-based method significantly enhances keypoint detection accuracy and task success rates, providing a more flexible and general solution for robotic garment manipulation. In addition, this research also underscores the potential of VLMs to unify various garment manipulation tasks within a single framework, paving the way for broader applications in home automation and assistive robotics for future.

Fan Cui, Liyong Guo, Quandong Wang et al.

In this paper, we investigate representation learning for low-resource keyword spotting (KWS). The main challenges of KWS are limited labeled data and limited available device resources. To address those challenges, we explore representation learning for KWS by self-supervised contrastive learning and self-training with pretrained model. First, local-global contrastive siamese networks (LGCSiam) are designed to learn similar utterance-level representations for similar audio samplers by proposed local-global contrastive loss without requiring ground-truth. Second, a self-supervised pretrained Wav2Vec 2.0 model is applied as a constraint module (WVC) to force the KWS model to learn frame-level acoustic representations. By the LGCSiam and WVC modules, the proposed small-footprint KWS model can be pretrained with unlabeled data. Experiments on speech commands dataset show that the self-training WVC module and the self-supervised LGCSiam module significantly improve accuracy, especially in the case of training on a small labeled dataset.

Jun Wang, Weixun Li, Changyu Hou et al.

Contrastive learning has emerged as a powerful tool for graph representation learning. However, most contrastive learning methods learn features of graphs with fixed coarse-grained scale, which might underestimate either local or global information. To capture more hierarchical and richer representation, we propose a novel Hierarchical Contrastive Learning (HCL) framework that explicitly learns graph representation in a hierarchical manner. Specifically, HCL includes two key components: a novel adaptive Learning to Pool (L2Pool) method to construct more reasonable multi-scale graph topology for more comprehensive contrastive objective, a novel multi-channel pseudo-siamese network to further enable more expressive learning of mutual information within each scale. Comprehensive experimental results show HCL achieves competitive performance on 12 datasets involving node classification, node clustering and graph classification. In addition, the visualization of learned representation reveals that HCL successfully captures meaningful characteristics of graphs.

Aoqi Guo, Junnan Wu, Peng Gao et al.

Recently, deep learning-based beamforming algorithms have shown promising performance in target speech extraction tasks. However, most systems do not fully utilize spatial information. In this paper, we propose a target speech extraction network that utilizes spatial information to enhance the performance of neural beamformer. To achieve this, we first use the UNet-TCN structure to model input features and improve the estimation accuracy of the speech pre-separation module by avoiding information loss caused by direct dimensionality reduction in other models. Furthermore, we introduce a multi-head cross-attention mechanism that enhances the neural beamformer's perception of spatial information by making full use of the spatial information received by the array. Experimental results demonstrate that our approach, which incorporates a more reasonable target mask estimation network and a spatial information-based cross-attention mechanism into the neural beamformer, effectively improves speech separation performance.

Jiayi Lei, Renrui Zhang, Xiangfei Hu et al.

With the rapid development of diffusion models, text-to-image(T2I) models have made significant progress, showcasing impressive abilities in prompt following and image generation. Recently launched models such as FLUX.1 and Ideogram2.0, along with others like Dall-E3 and Stable Diffusion 3, have demonstrated exceptional performance across various complex tasks, raising questions about whether T2I models are moving towards general-purpose applicability. Beyond traditional image generation, these models exhibit capabilities across a range of fields, including controllable generation, image editing, video, audio, 3D, and motion generation, as well as computer vision tasks like semantic segmentation and depth estimation. However, current evaluation frameworks are insufficient to comprehensively assess these models' performance across expanding domains. To thoroughly evaluate these models, we developed the IMAGINE-E and tested six prominent models: FLUX.1, Ideogram2.0, Midjourney, Dall-E3, Stable Diffusion 3, and Jimeng. Our evaluation is divided into five key domains: structured output generation, realism, and physical consistency, specific domain generation, challenging scenario generation, and multi-style creation tasks. This comprehensive assessment highlights each model's strengths and limitations, particularly the outstanding performance of FLUX.1 and Ideogram2.0 in structured and specific domain tasks, underscoring the expanding applications and potential of T2I models as foundational AI tools. This study provides valuable insights into the current state and future trajectory of T2I models as they evolve towards general-purpose usability. Evaluation scripts will be released at https://github.com/jylei16/Imagine-e.

Shilin Yan, Renrui Zhang, Ziyu Guo et al.

Recently, video object segmentation (VOS) referred by multi-modal signals, e.g., language and audio, has evoked increasing attention in both industry and academia. It is challenging for exploring the semantic alignment within modalities and the visual correspondence across frames. However, existing methods adopt separate network architectures for different modalities, and neglect the inter-frame temporal interaction with references. In this paper, we propose MUTR, a Multi-modal Unified Temporal transformer for Referring video object segmentation. With a unified framework for the first time, MUTR adopts a DETR-style transformer and is capable of segmenting video objects designated by either text or audio reference. Specifically, we introduce two strategies to fully explore the temporal relations between videos and multi-modal signals. Firstly, for low-level temporal aggregation before the transformer, we enable the multi-modal references to capture multi-scale visual cues from consecutive video frames. This effectively endows the text or audio signals with temporal knowledge and boosts the semantic alignment between modalities. Secondly, for high-level temporal interaction after the transformer, we conduct inter-frame feature communication for different object embeddings, contributing to better object-wise correspondence for tracking along the video. On Ref-YouTube-VOS and AVSBench datasets with respective text and audio references, MUTR achieves +4.2% and +8.7% J&F improvements to state-of-the-art methods, demonstrating our significance for unified multi-modal VOS. Code is released at https://github.com/OpenGVLab/MUTR.

Siyuan Huang, Zhengkai Jiang, Hao Dong et al.

Foundation models have made significant strides in various applications, including text-to-image generation, panoptic segmentation, and natural language processing. This paper presents Instruct2Act, a framework that utilizes Large Language Models to map multi-modal instructions to sequential actions for robotic manipulation tasks. Specifically, Instruct2Act employs the LLM model to generate Python programs that constitute a comprehensive perception, planning, and action loop for robotic tasks. In the perception section, pre-defined APIs are used to access multiple foundation models where the Segment Anything Model (SAM) accurately locates candidate objects, and CLIP classifies them. In this way, the framework leverages the expertise of foundation models and robotic abilities to convert complex high-level instructions into precise policy codes. Our approach is adjustable and flexible in accommodating various instruction modalities and input types and catering to specific task demands. We validated the practicality and efficiency of our approach by assessing it on robotic tasks in different scenarios within tabletop manipulation domains. Furthermore, our zero-shot method outperformed many state-of-the-art learning-based policies in several tasks. The code for our proposed approach is available at https://github.com/OpenGVLab/Instruct2Act, serving as a robust benchmark for high-level robotic instruction tasks with assorted modality inputs.

Siyuan Huang, Bo Zhang, Botian Shi et al.

Although Domain Generalization (DG) problem has been fast-growing in the 2D image tasks, its exploration on 3D point cloud data is still insufficient and challenged by more complex and uncertain cross-domain variances with uneven inter-class modality distribution. In this paper, different from previous 2D DG works, we focus on the 3D DG problem and propose a Single-dataset Unified Generalization (SUG) framework that only leverages a single source dataset to alleviate the unforeseen domain differences faced by a well-trained source model. Specifically, we first design a Multi-grained Sub-domain Alignment (MSA) method, which can constrain the learned representations to be domain-agnostic and discriminative, by performing a multi-grained feature alignment process between the splitted sub-domains from the single source dataset. Then, a Sample-level Domain-aware Attention (SDA) strategy is presented, which can selectively enhance easy-to-adapt samples from different sub-domains according to the sample-level inter-domain distance to avoid the negative transfer. Experiments demonstrate that our SUG can boost the generalization ability for unseen target domains, even outperforming the existing unsupervised domain adaptation methods that have to access extensive target domain data. Our code is available at https://github.com/SiyuanHuang95/SUG.

Renrui Zhang, Zhengkai Jiang, Ziyu Guo et al.

Driven by large-data pre-training, Segment Anything Model (SAM) has been demonstrated as a powerful and promptable framework, revolutionizing the segmentation models. Despite the generality, customizing SAM for specific visual concepts without man-powered prompting is under explored, e.g., automatically segmenting your pet dog in different images. In this paper, we propose a training-free Personalization approach for SAM, termed as PerSAM. Given only a single image with a reference mask, PerSAM first localizes the target concept by a location prior, and segments it within other images or videos via three techniques: target-guided attention, target-semantic prompting, and cascaded post-refinement. In this way, we effectively adapt SAM for private use without any training. To further alleviate the mask ambiguity, we present an efficient one-shot fine-tuning variant, PerSAM-F. Freezing the entire SAM, we introduce two learnable weights for multi-scale masks, only training 2 parameters within 10 seconds for improved performance. To demonstrate our efficacy, we construct a new segmentation dataset, PerSeg, for personalized evaluation, and test our methods on video object segmentation with competitive performance. Besides, our approach can also enhance DreamBooth to personalize Stable Diffusion for text-to-image generation, which discards the background disturbance for better target appearance learning. Code is released at https://github.com/ZrrSkywalker/Personalize-SAM

Kunchang Li, Yali Wang, Peng Gao et al.

It is a challenging task to learn rich and multi-scale spatiotemporal semantics from high-dimensional videos, due to large local redundancy and complex global dependency between video frames. The recent advances in this research have been mainly driven by 3D convolutional neural networks and vision transformers. Although 3D convolution can efficiently aggregate local context to suppress local redundancy from a small 3D neighborhood, it lacks the capability to capture global dependency because of the limited receptive field. Alternatively, vision transformers can effectively capture long-range dependency by self-attention mechanism, while having the limitation on reducing local redundancy with blind similarity comparison among all the tokens in each layer. Based on these observations, we propose a novel Unified transFormer (UniFormer) which seamlessly integrates merits of 3D convolution and spatiotemporal self-attention in a concise transformer format, and achieves a preferable balance between computation and accuracy. Different from traditional transformers, our relation aggregator can tackle both spatiotemporal redundancy and dependency, by learning local and global token affinity respectively in shallow and deep layers. We conduct extensive experiments on the popular video benchmarks, e.g., Kinetics-400, Kinetics-600, and Something-Something V1&V2. With only ImageNet-1K pretraining, our UniFormer achieves 82.9%/84.8% top-1 accuracy on Kinetics-400/Kinetics-600, while requiring 10x fewer GFLOPs than other state-of-the-art methods. For Something-Something V1 and V2, our UniFormer achieves new state-of-the-art performances of 60.9% and 71.2% top-1 accuracy respectively. Code is available at https://github.com/Sense-X/UniFormer.

Renrui Zhang, Ziyu Guo, Wei Zhang et al.

Recently, zero-shot and few-shot learning via Contrastive Vision-Language Pre-training (CLIP) have shown inspirational performance on 2D visual recognition, which learns to match images with their corresponding texts in open-vocabulary settings. However, it remains under explored that whether CLIP, pre-trained by large-scale image-text pairs in 2D, can be generalized to 3D recognition. In this paper, we identify such a setting is feasible by proposing PointCLIP, which conducts alignment between CLIP-encoded point cloud and 3D category texts. Specifically, we encode a point cloud by projecting it into multi-view depth maps without rendering, and aggregate the view-wise zero-shot prediction to achieve knowledge transfer from 2D to 3D. On top of that, we design an inter-view adapter to better extract the global feature and adaptively fuse the few-shot knowledge learned from 3D into CLIP pre-trained in 2D. By just fine-tuning the lightweight adapter in the few-shot settings, the performance of PointCLIP could be largely improved. In addition, we observe the complementary property between PointCLIP and classical 3D-supervised networks. By simple ensembling, PointCLIP boosts baseline's performance and even surpasses state-of-the-art models. Therefore, PointCLIP is a promising alternative for effective 3D point cloud understanding via CLIP under low resource cost and data regime. We conduct thorough experiments on widely-adopted ModelNet10, ModelNet40 and the challenging ScanObjectNN to demonstrate the effectiveness of PointCLIP. The code is released at https://github.com/ZrrSkywalker/PointCLIP.

Peng Gao, Minghang Zheng, Xiaogang Wang et al.

The recently proposed Detection Transformer (DETR) model successfully applies Transformer to objects detection and achieves comparable performance with two-stage object detection frameworks, such as Faster-RCNN. However, DETR suffers from its slow convergence. Training DETR from scratch needs 500 epochs to achieve a high accuracy. To accelerate its convergence, we propose a simple yet effective scheme for improving the DETR framework, namely Spatially Modulated Co-Attention (SMCA) mechanism. The core idea of SMCA is to conduct location-aware co-attention in DETR by constraining co-attention responses to be high near initially estimated bounding box locations. Our proposed SMCA increases DETR's convergence speed by replacing the original co-attention mechanism in the decoder while keeping other operations in DETR unchanged. Furthermore, by integrating multi-head and scale-selection attention designs into SMCA, our fully-fledged SMCA can achieve better performance compared to DETR with a dilated convolution-based backbone (45.6 mAP at 108 epochs vs. 43.3 mAP at 500 epochs). We perform extensive ablation studies on COCO dataset to validate SMCA. Code is released at https://github.com/gaopengcuhk/SMCA-DETR .

Xiangyang Zhu, Renrui Zhang, Bowei He et al.

To reduce the reliance on large-scale datasets, recent works in 3D segmentation resort to few-shot learning. Current 3D few-shot segmentation methods first pre-train models on 'seen' classes, and then evaluate their generalization performance on 'unseen' classes. However, the prior pre-training stage not only introduces excessive time overhead but also incurs a significant domain gap on 'unseen' classes. To tackle these issues, we propose a Non-parametric Network for few-shot 3D Segmentation, Seg-NN, and its Parametric variant, Seg-PN. Without training, Seg-NN extracts dense representations by hand-crafted filters and achieves comparable performance to existing parametric models. Due to the elimination of pre-training, Seg-NN can alleviate the domain gap issue and save a substantial amount of time. Based on Seg-NN, Seg-PN only requires training a lightweight QUEry-Support Transferring (QUEST) module, which enhances the interaction between the support set and query set. Experiments suggest that Seg-PN outperforms previous state-of-the-art method by +4.19% and +7.71% mIoU on S3DIS and ScanNet datasets respectively, while reducing training time by -90%, indicating its effectiveness and efficiency.

Peng Gao, Peng Wang, Feng Gao et al.

As a long-term vision in the field of artificial intelligence, the core goal of embodied intelligence is to improve the perception, understanding, and interaction capabilities of agents and the environment. Vision-language navigation (VLN), as a critical research path to achieve embodied intelligence, focuses on exploring how agents use natural language to communicate effectively with humans, receive and understand instructions, and ultimately rely on visual information to achieve accurate navigation. VLN integrates artificial intelligence, natural language processing, computer vision, and robotics. This field faces technical challenges but shows potential for application such as human-computer interaction. However, due to the complex process involved from language understanding to action execution, VLN faces the problem of aligning visual information and language instructions, improving generalization ability, and many other challenges. This survey systematically reviews the research progress of VLN and details the research direction of VLN with embodied intelligence. After a detailed summary of its system architecture and research based on methods and commonly used benchmark datasets, we comprehensively analyze the problems and challenges faced by current research and explore the future development direction of this field, aiming to provide a practical reference for researchers.

Peng Gao, Le Zhuo, Dongyang Liu et al.

Sora unveils the potential of scaling Diffusion Transformer for generating photorealistic images and videos at arbitrary resolutions, aspect ratios, and durations, yet it still lacks sufficient implementation details. In this technical report, we introduce the Lumina-T2X family - a series of Flow-based Large Diffusion Transformers (Flag-DiT) equipped with zero-initialized attention, as a unified framework designed to transform noise into images, videos, multi-view 3D objects, and audio clips conditioned on text instructions. By tokenizing the latent spatial-temporal space and incorporating learnable placeholders such as [nextline] and [nextframe] tokens, Lumina-T2X seamlessly unifies the representations of different modalities across various spatial-temporal resolutions. This unified approach enables training within a single framework for different modalities and allows for flexible generation of multimodal data at any resolution, aspect ratio, and length during inference. Advanced techniques like RoPE, RMSNorm, and flow matching enhance the stability, flexibility, and scalability of Flag-DiT, enabling models of Lumina-T2X to scale up to 7 billion parameters and extend the context window to 128K tokens. This is particularly beneficial for creating ultra-high-definition images with our Lumina-T2I model and long 720p videos with our Lumina-T2V model. Remarkably, Lumina-T2I, powered by a 5-billion-parameter Flag-DiT, requires only 35% of the training computational costs of a 600-million-parameter naive DiT. Our further comprehensive analysis underscores Lumina-T2X's preliminary capability in resolution extrapolation, high-resolution editing, generating consistent 3D views, and synthesizing videos with seamless transitions. We expect that the open-sourcing of Lumina-T2X will further foster creativity, transparency, and diversity in the generative AI community.

Xiangyang Zhu, Renrui Zhang, Bowei He et al.

To reduce the reliance on large-scale datasets, recent works in 3D segmentation resort to few-shot learning. Current 3D few-shot semantic segmentation methods first pre-train the models on `seen' classes, and then evaluate their generalization performance on `unseen' classes. However, the prior pre-training stage not only introduces excessive time overhead, but also incurs a significant domain gap on `unseen' classes. To tackle these issues, we propose an efficient Training-free Few-shot 3D Segmentation netwrok, TFS3D, and a further training-based variant, TFS3D-T. Without any learnable parameters, TFS3D extracts dense representations by trigonometric positional encodings, and achieves comparable performance to previous training-based methods. Due to the elimination of pre-training, TFS3D can alleviate the domain gap issue and save a substantial amount of time. Building upon TFS3D, TFS3D-T only requires to train a lightweight query-support transferring attention (QUEST), which enhances the interaction between the few-shot query and support data. Experiments demonstrate TFS3D-T improves previous state-of-the-art methods by +6.93% and +17.96% mIoU respectively on S3DIS and ScanNet, while reducing the training time by -90%, indicating superior effectiveness and efficiency.

Li Wang, Rongzhi Gu, Weiji Zhuang et al.

Keyword spotting (KWS) and speaker verification (SV) are two important tasks in speech applications. Research shows that the state-of-art KWS and SV models are trained independently using different datasets since they expect to learn distinctive acoustic features. However, humans can distinguish language content and the speaker identity simultaneously. Motivated by this, we believe it is important to explore a method that can effectively extract common features while decoupling task-specific features. Bearing this in mind, a two-branch deep network (KWS branch and SV branch) with the same network structure is developed and a novel decoupling feature learning method is proposed to push up the performance of KWS and SV simultaneously where speaker-invariant keyword representations and keyword-invariant speaker representations are expected respectively. Experiments are conducted on Google Speech Commands Dataset (GSCD). The results demonstrate that the orthogonality regularization helps the network to achieve SOTA EER of 1.31% and 1.87% on KWS and SV, respectively.

Kexue Fu, Peng Gao, Renrui Zhang et al.

In this paper, we propose a simple and general framework for self-supervised point cloud representation learning. Human beings understand the 3D world by extracting two levels of information and establishing the relationship between them. One is the global shape of an object, and the other is the local structures of it. However, few existing studies in point cloud representation learning explored how to learn both global shapes and local-to-global relationships without a specified network architecture. Inspired by how human beings understand the world, we utilize knowledge distillation to learn both global shape information and the relationship between global shape and local structures. At the same time, we combine contrastive learning with knowledge distillation to make the teacher network be better updated. Our method achieves the state-of-the-art performance on linear classification and multiple other downstream tasks. Especially, we develop a variant of ViT for 3D point cloud feature extraction, which also achieves comparable results with existing backbones when combined with our framework, and visualization of the attention maps show that our model does understand the point cloud by combining the global shape information and multiple local structural information, which is consistent with the inspiration of our representation learning method. Our code will be released soon.

Sheng Xu, Yanjing Li, Teli Ma et al.

Vision transformers (ViTs) have demonstrated great potential in various visual tasks, but suffer from expensive computational and memory cost problems when deployed on resource-constrained devices. In this paper, we introduce a ternary vision transformer (TerViT) to ternarize the weights in ViTs, which are challenged by the large loss surface gap between real-valued and ternary parameters. To address the issue, we introduce a progressive training scheme by first training 8-bit transformers and then TerViT, and achieve a better optimization than conventional methods. Furthermore, we introduce channel-wise ternarization, by partitioning each matrix to different channels, each of which is with an unique distribution and ternarization interval. We apply our methods to popular DeiT and Swin backbones, and extensive results show that we can achieve competitive performance. For example, TerViT can quantize Swin-S to 13.1MB model size while achieving above 79% Top-1 accuracy on ImageNet dataset.

Ziteng Cui, Yingying Zhu, Lin Gu et al.

Image restoration algorithms such as super resolution (SR) are indispensable pre-processing modules for object detection in degraded images. However, most of these algorithms assume the degradation is fixed and known a priori. When the real degradation is unknown or differs from assumption, both the pre-processing module and the consequent high-level task such as object detection would fail. Here, we propose a novel framework, RestoreDet, to detect objects in degraded low resolution images. RestoreDet utilizes the downsampling degradation as a kind of transformation for self-supervised signals to explore the equivariant representation against various resolutions and other degradation conditions. Specifically, we learn this intrinsic visual structure by encoding and decoding the degradation transformation from a pair of original and randomly degraded images. The framework could further take the advantage of advanced SR architectures with an arbitrary resolution restoring decoder to reconstruct the original correspondence from the degraded input image. Both the representation learning and object detection are optimized jointly in an end-to-end training fashion. RestoreDet is a generic framework that could be implemented on any mainstream object detection architectures. The extensive experiment shows that our framework based on CenterNet has achieved superior performance compared with existing methods when facing variant degradation situations. Our code would be released soon.

Liang Pan, Tong Wu, Zhongang Cai et al.

As real-scanned point clouds are mostly partial due to occlusions and viewpoints, reconstructing complete 3D shapes based on incomplete observations becomes a fundamental problem for computer vision. With a single incomplete point cloud, it becomes the partial point cloud completion problem. Given multiple different observations, 3D reconstruction can be addressed by performing partial-to-partial point cloud registration. Recently, a large-scale Multi-View Partial (MVP) point cloud dataset has been released, which consists of over 100,000 high-quality virtual-scanned partial point clouds. Based on the MVP dataset, this paper reports methods and results in the Multi-View Partial Point Cloud Challenge 2021 on Completion and Registration. In total, 128 participants registered for the competition, and 31 teams made valid submissions. The top-ranked solutions will be analyzed, and then we will discuss future research directions.

Peng Gao, Brian Reily, Rui Guo et al.

Collaborative localization is an essential capability for a team of robots such as connected vehicles to collaboratively estimate object locations from multiple perspectives with reliant cooperation. To enable collaborative localization, four key challenges must be addressed, including modeling complex relationships between observed objects, fusing observations from an arbitrary number of collaborating robots, quantifying localization uncertainty, and addressing latency of robot communications. In this paper, we introduce a novel approach that integrates uncertainty-aware spatiotemporal graph learning and model-based state estimation for a team of robots to collaboratively localize objects. Specifically, we introduce a new uncertainty-aware graph learning model that learns spatiotemporal graphs to represent historical motions of the objects observed by each robot over time and provides uncertainties in object localization. Moreover, we propose a novel method for integrated learning and model-based state estimation, which fuses asynchronous observations obtained from an arbitrary number of robots for collaborative localization. We evaluate our approach in two collaborative object localization scenarios in simulations and on real robots. Experimental results show that our approach outperforms previous methods and achieves state-of-the-art performance on asynchronous collaborative localization.

Ankit P. Shah, Shijie Geng, Peng Gao et al.

In previous work, we have proposed the Audio-Visual Scene-Aware Dialog (AVSD) task, collected an AVSD dataset, developed AVSD technologies, and hosted an AVSD challenge track at both the 7th and 8th Dialog System Technology Challenges (DSTC7, DSTC8). In these challenges, the best-performing systems relied heavily on human-generated descriptions of the video content, which were available in the datasets but would be unavailable in real-world applications. To promote further advancements for real-world applications, we proposed a third AVSD challenge, at DSTC10, with two modifications: 1) the human-created description is unavailable at inference time, and 2) systems must demonstrate temporal reasoning by finding evidence from the video to support each answer. This paper introduces the new task that includes temporal reasoning and our new extension of the AVSD dataset for DSTC10, for which we collected human-generated temporal reasoning data. We also introduce a baseline system built using an AV-transformer, which we released along with the new dataset. Finally, this paper introduces a new system that extends our baseline system with attentional multimodal fusion, joint student-teacher learning (JSTL), and model combination techniques, achieving state-of-the-art performances on the AVSD datasets for DSTC7, DSTC8, and DSTC10. We also propose two temporal reasoning methods for AVSD: one attention-based, and one based on a time-domain region proposal network.

Lei Shi, Kai Shuang, Shijie Geng et al.

Inspired by the success of BERT, several multimodal representation learning approaches have been proposed that jointly represent image and text. These approaches achieve superior performance by capturing high-level semantic information from large-scale multimodal pretraining. In particular, LXMERT and UNITER adopt visual region feature regression and label classification as pretext tasks. However, they tend to suffer from the problems of noisy labels and sparse semantic annotations, based on the visual features having been pretrained on a crowdsourced dataset with limited and inconsistent semantic labeling. To overcome these issues, we propose unbiased Dense Contrastive Visual-Linguistic Pretraining (DCVLP), which replaces the region regression and classification with cross-modality region contrastive learning that requires no annotations. Two data augmentation strategies (Mask Perturbation and Intra-/Inter-Adversarial Perturbation) are developed to improve the quality of negative samples used in contrastive learning. Overall, DCVLP allows cross-modality dense region contrastive learning in a self-supervised setting independent of any object annotations. We compare our method against prior visual-linguistic pretraining frameworks to validate the superiority of dense contrastive learning on multimodal representation learning.