Bo Wan

Haiwen Diao, Bo Wan, Ying Zhang et al.

Parameter-efficient transfer learning (PETL), i.e., fine-tuning a small portion of parameters, is an effective strategy for adapting pre-trained models to downstream domains. To further reduce the memory demand, recent PETL works focus on the more valuable memory-efficient characteristic. In this paper, we argue that the scalability, adaptability, and generalizability of state-of-the-art methods are hindered by structural dependency and pertinency on specific pre-trained backbones. To this end, we propose a new memory-efficient PETL strategy, Universal Parallel Tuning (UniPT), to mitigate these weaknesses. Specifically, we facilitate the transfer process via a lightweight and learnable parallel network, which consists of: 1) A parallel interaction module that decouples the sequential connections and processes the intermediate activations detachedly from the pre-trained network. 2) A confidence aggregation module that learns optimal strategies adaptively for integrating cross-layer features. We evaluate UniPT with different backbones (e.g., T5, VSE$\infty$, CLIP4Clip, Clip-ViL, and MDETR) on various vision-and-language and pure NLP tasks. Extensive ablations on 18 datasets have validated that UniPT can not only dramatically reduce memory consumption and outperform the best competitor, but also achieve competitive performance over other plain PETL methods with lower training memory overhead. Our code is publicly available at: https://github.com/Paranioar/UniPT.

Lucas Beyer, Bo Wan, Gagan Madan et al. · deepmind

There has been a recent explosion of computer vision models which perform many tasks and are composed of an image encoder (usually a ViT) and an autoregressive decoder (usually a Transformer). However, most of this work simply presents one system and its results, leaving many questions regarding design decisions and trade-offs of such systems unanswered. In this work, we aim to provide such answers. We take a close look at autoregressive decoders for multi-task learning in multimodal computer vision, including classification, captioning, visual question answering, and optical character recognition. Through extensive systematic experiments, we study the effects of task and data mixture, training and regularization hyperparameters, conditioning type and specificity, modality combination, and more. Importantly, we compare these to well-tuned single-task baselines to highlight the cost incurred by multi-tasking. A key finding is that a small decoder learned on top of a frozen pretrained encoder works surprisingly well. We call this setup locked-image tuning with decoder (LiT-decoder). It can be seen as teaching a decoder to interact with a pretrained vision model via natural language.

Haiwen Diao, Bo Wan, Xu Jia et al.

Parameter-efficient transfer learning (PETL) has emerged as a flourishing research field for adapting large pre-trained models to downstream tasks, greatly reducing trainable parameters while grappling with memory challenges during fine-tuning. To address it, memory-efficient series (METL) avoid backpropagating gradients through the large backbone. However, they compromise by exclusively relying on frozen intermediate outputs and limiting the exhaustive exploration of prior knowledge from pre-trained models. Moreover, the dependency and redundancy between cross-layer features are frequently overlooked, thereby submerging more discriminative representations and causing an inherent performance gap (vs. conventional PETL methods). Hence, we propose an innovative METL strategy called SHERL for resource-limited scenarios to decouple the entire adaptation into two successive and complementary processes. In the early route, intermediate outputs are consolidated via an anti-redundancy operation, enhancing their compatibility for subsequent interactions; thereby in the late route, utilizing minimal late pre-trained layers could alleviate the peak demand on memory overhead and regulate these fairly flexible features into more adaptive and powerful representations for new domains. Extensive ablations on vision-and-language and language-only tasks show that SHERL combines the strengths of both parameter and memory-efficient techniques, performing on-par or better across diverse architectures with lower memory during fine-tuning. Our code is publicly available at: https://github.com/Paranioar/SHERL.

Bo Wan, Yongfei Liu, Desen Zhou et al.

Human object interaction (HOI) detection plays a crucial role in human-centric scene understanding and serves as a fundamental building-block for many vision tasks. One generalizable and scalable strategy for HOI detection is to use weak supervision, learning from image-level annotations only. This is inherently challenging due to ambiguous human-object associations, large search space of detecting HOIs and highly noisy training signal. A promising strategy to address those challenges is to exploit knowledge from large-scale pretrained models (e.g., CLIP), but a direct knowledge distillation strategy~\citep{liao2022gen} does not perform well on the weakly-supervised setting. In contrast, we develop a CLIP-guided HOI representation capable of incorporating the prior knowledge at both image level and HOI instance level, and adopt a self-taught mechanism to prune incorrect human-object associations. Experimental results on HICO-DET and V-COCO show that our method outperforms the previous works by a sizable margin, showing the efficacy of our HOI representation.

Bo Wan, Tinne Tuytelaars

In this paper, we investigate the task of zero-shot human-object interaction (HOI) detection, a novel paradigm for identifying HOIs without the need for task-specific annotations. To address this challenging task, we employ CLIP, a large-scale pre-trained vision-language model (VLM), for knowledge distillation on multiple levels. Specifically, we design a multi-branch neural network that leverages CLIP for learning HOI representations at various levels, including global images, local union regions encompassing human-object pairs, and individual instances of humans or objects. To train our model, CLIP is utilized to generate HOI scores for both global images and local union regions that serve as supervision signals. The extensive experiments demonstrate the effectiveness of our novel multi-level CLIP knowledge integration strategy. Notably, the model achieves strong performance, which is even comparable with some fully-supervised and weakly-supervised methods on the public HICO-DET benchmark.

Yongfei Liu, Bo Wan, Lin Ma et al.

Visual grounding, which aims to build a correspondence between visual objects and their language entities, plays a key role in cross-modal scene understanding. One promising and scalable strategy for learning visual grounding is to utilize weak supervision from only image-caption pairs. Previous methods typically rely on matching query phrases directly to a precomputed, fixed object candidate pool, which leads to inaccurate localization and ambiguous matching due to lack of semantic relation constraints. In our paper, we propose a novel context-aware weakly-supervised learning method that incorporates coarse-to-fine object refinement and entity relation modeling into a two-stage deep network, capable of producing more accurate object representation and matching. To effectively train our network, we introduce a self-taught regression loss for the proposal locations and a classification loss based on parsed entity relations. Extensive experiments on two public benchmarks Flickr30K Entities and ReferItGame demonstrate the efficacy of our weakly grounding framework. The results show that we outperform the previous methods by a considerable margin, achieving 59.27\% top-1 accuracy in Flickr30K Entities and 37.68\% in the ReferItGame dataset respectively (Code is available at https://github.com/youngfly11/ReIR-WeaklyGrounding.pytorch.git).

Yongfei Liu, Bo Wan, Xiaodan Zhu et al.

Visual grounding is a ubiquitous building block in many vision-language tasks and yet remains challenging due to large variations in visual and linguistic features of grounding entities, strong context effect and the resulting semantic ambiguities. Prior works typically focus on learning representations of individual phrases with limited context information. To address their limitations, this paper proposes a language-guided graph representation to capture the global context of grounding entities and their relations, and develop a cross-modal graph matching strategy for the multiple-phrase visual grounding task. In particular, we introduce a modular graph neural network to compute context-aware representations of phrases and object proposals respectively via message propagation, followed by a graph-based matching module to generate globally consistent localization of grounding phrases. We train the entire graph neural network jointly in a two-stage strategy and evaluate it on the Flickr30K Entities benchmark. Extensive experiments show that our method outperforms the prior state of the arts by a sizable margin, evidencing the efficacy of our grounding framework. Code is available at "https://github.com/youngfly11/LCMCG-PyTorch".

Bo Wan, Michael Tschannen, Yongqin Xian et al.

Image captioning has been shown as an effective pretraining method similar to contrastive pretraining. However, the incorporation of location-aware information into visual pretraining remains an area with limited research. In this paper, we propose a simple visual pretraining method with location-aware captioners (LocCa). LocCa uses a simple image captioner task interface, to teach a model to read out rich information, i.e. bounding box coordinates, and captions, conditioned on the image pixel input. Thanks to the multitask capabilities of an encoder-decoder architecture, we show that an image captioner can easily handle multiple tasks during pretraining. Our experiments demonstrate that LocCa outperforms standard captioners significantly on localization downstream tasks while maintaining comparable performance on holistic tasks.

Mingxiao Li, Bo Wan, Marie-Francine Moens et al.

In recent years, diffusion models have made remarkable strides in text-to-video generation, sparking a quest for enhanced control over video outputs to more accurately reflect user intentions. Traditional efforts predominantly focus on employing either semantic cues, like images or depth maps, or motion-based conditions, like moving sketches or object bounding boxes. Semantic inputs offer a rich scene context but lack detailed motion specificity; conversely, motion inputs provide precise trajectory information but miss the broader semantic narrative. For the first time, we integrate both semantic and motion cues within a diffusion model for video generation, as demonstrated in Fig 1. To this end, we introduce the Scene and Motion Conditional Diffusion (SMCD), a novel methodology for managing multimodal inputs. It incorporates a recognized motion conditioning module and investigates various approaches to integrate scene conditions, promoting synergy between different modalities. For model training, we separate the conditions for the two modalities, introducing a two-stage training pipeline. Experimental results demonstrate that our design significantly enhances video quality, motion precision, and semantic coherence.

Hovhannes Margaryan, Bo Wan, Tinne Tuytelaars

This paper introduces a novel approach to aesthetic quality improvement in pre-trained text-to-image diffusion models when given a simple prompt. Our method, dubbed Prompt Embedding Optimization (PEO), leverages a pre-trained text-to-image diffusion model as a backbone and optimizes the text embedding of a given simple and uncurated prompt to enhance the visual quality of the generated image. We achieve this by a tripartite objective function that improves the aesthetic fidelity of the generated image, ensures adherence to the optimized text embedding, and minimal divergence from the initial prompt. The latter is accomplished through a prompt preservation term. Additionally, PEO is training-free and backbone-independent. Quantitative and qualitative evaluations confirm the effectiveness of the proposed method, exceeding or equating the performance of state-of-the-art text-to-image and prompt adaptation methods.

Nan Luo, Chenglin Ye, Jiaxu Li et al.

Neural Radiance Fields (NeRF) has gained significant attention for its prominent implicit 3D representation and realistic novel view synthesis capabilities. Available works unexceptionally employ straight-line volume rendering, which struggles to handle sophisticated lightpath scenarios and introduces geometric ambiguities during training, particularly evident when processing motion-blurred images. To address these challenges, this work proposes a novel deblur neural radiance field, Is-NeRF, featuring explicit lightpath modeling in real-world environments. By unifying six common light propagation phenomena through an in-scattering representation, we establish a new scattering-aware volume rendering pipeline adaptable to complex lightpaths. Additionally, we introduce an adaptive learning strategy that enables autonomous determining of scattering directions and sampling intervals to capture finer object details. The proposed network jointly optimizes NeRF parameters, scattering parameters, and camera motions to recover fine-grained scene representations from blurry images. Comprehensive evaluations demonstrate that it effectively handles complex real-world scenarios, outperforming state-of-the-art approaches in generating high-fidelity images with accurate geometric details.

Xiao Liang, Jiawei Hu, Di Wang et al.

Vision-language models (VLMs) are prone to hallucinations that critically compromise reliability in medical applications. While preference optimization can mitigate these hallucinations through clinical feedback, its implementation faces challenges such as clinically irrelevant training samples, imbalanced data distributions, and prohibitive expert annotation costs. To address these challenges, we introduce CheXPO, a Chest X-ray Preference Optimization strategy that combines confidence-similarity joint mining with counterfactual rationale. Our approach begins by synthesizing a unified, fine-grained multi-task chest X-ray visual instruction dataset across different question types for supervised fine-tuning (SFT). We then identify hard examples through token-level confidence analysis of SFT failures and use similarity-based retrieval to expand hard examples for balancing preference sample distributions, while synthetic counterfactual rationales provide fine-grained clinical preferences, eliminating the need for additional expert input. Experiments show that CheXPO achieves 8.93% relative performance gain using only 5% of SFT samples, reaching state-of-the-art performance across diverse clinical tasks and providing a scalable, interpretable solution for real-world radiology applications.

Vasu Agrawal, Akinniyi Akinyemi, Kathryn Alvero et al.

Human communication involves a complex interplay of verbal and nonverbal signals, essential for conveying meaning and achieving interpersonal goals. To develop socially intelligent AI technologies, it is crucial to develop models that can both comprehend and generate dyadic behavioral dynamics. To this end, we introduce the Seamless Interaction Dataset, a large-scale collection of over 4,000 hours of face-to-face interaction footage from over 4,000 participants in diverse contexts. This dataset enables the development of AI technologies that understand dyadic embodied dynamics, unlocking breakthroughs in virtual agents, telepresence experiences, and multimodal content analysis tools. We also develop a suite of models that utilize the dataset to generate dyadic motion gestures and facial expressions aligned with human speech. These models can take as input both the speech and visual behavior of their interlocutors. We present a variant with speech from an LLM model and integrations with 2D and 3D rendering methods, bringing us closer to interactive virtual agents. Additionally, we describe controllable variants of our motion models that can adapt emotional responses and expressivity levels, as well as generating more semantically-relevant gestures. Finally, we discuss methods for assessing the quality of these dyadic motion models, which are demonstrating the potential for more intuitive and responsive human-AI interactions.

Qian He, Desen Zhou, Bo Wan et al.

Reconstructing 3D object from a single image (RGB or depth) is a fundamental problem in visual scene understanding and yet remains challenging due to its ill-posed nature and complexity in real-world scenes. To address those challenges, we adopt a primitive-based representation for 3D object, and propose a two-stage graph network for primitive-based 3D object estimation, which consists of a sequential proposal module and a graph reasoning module. Given a 2D image, our proposal module first generates a sequence of 3D primitives from input image with local feature attention. Then the graph reasoning module performs joint reasoning on a primitive graph to capture the global shape context for each primitive. Such a framework is capable of taking into account rich geometry and semantic constraints during 3D structure recovery, producing 3D objects with more coherent structure even under challenging viewing conditions. We train the entire graph neural network in a stage-wise strategy and evaluate it on three benchmarks: Pix3D, ModelNet and NYU Depth V2. Extensive experiments show that our approach outperforms the previous state of the arts with a considerable margin.

Rongjie Li, Songyang Zhang, Bo Wan et al.

Scene graph generation is an important visual understanding task with a broad range of vision applications. Despite recent tremendous progress, it remains challenging due to the intrinsic long-tailed class distribution and large intra-class variation. To address these issues, we introduce a novel confidence-aware bipartite graph neural network with adaptive message propagation mechanism for unbiased scene graph generation. In addition, we propose an efficient bi-level data resampling strategy to alleviate the imbalanced data distribution problem in training our graph network. Our approach achieves superior or competitive performance over previous methods on several challenging datasets, including Visual Genome, Open Images V4/V6, demonstrating its effectiveness and generality.

Bo Wan, Desen Zhou, Yongfei Liu et al.

Reasoning human object interactions is a core problem in human-centric scene understanding and detecting such relations poses a unique challenge to vision systems due to large variations in human-object configurations, multiple co-occurring relation instances and subtle visual difference between relation categories. To address those challenges, we propose a multi-level relation detection strategy that utilizes human pose cues to capture global spatial configurations of relations and as an attention mechanism to dynamically zoom into relevant regions at human part level. Specifically, we develop a multi-branch deep network to learn a pose-augmented relation representation at three semantic levels, incorporating interaction context, object features and detailed semantic part cues. As a result, our approach is capable of generating robust predictions on fine-grained human object interactions with interpretable outputs. Extensive experimental evaluations on public benchmarks show that our model outperforms prior methods by a considerable margin, demonstrating its efficacy in handling complex scenes.