Jiamian Wang

Jiamian Wang, Zongliang Wu, Yulun Zhang et al.

Existing reconstruction models in snapshot compressive imaging systems (SCI) are trained with a single well-calibrated hardware instance, making their performance vulnerable to hardware shifts and limited in adapting to multiple hardware configurations. To facilitate cross-hardware learning, previous efforts attempt to directly collect multi-hardware data and perform centralized training, which is impractical due to severe user data privacy concerns and hardware heterogeneity across different platforms/institutions. In this study, we explicitly consider data privacy and heterogeneity in cooperatively optimizing SCI systems by proposing a Federated Hardware-Prompt learning (FedHP) framework. Rather than mitigating the client drift by rectifying the gradients, which only takes effect on the learning manifold but fails to solve the heterogeneity rooted in the input data space, FedHP learns a hardware-conditioned prompter to align inconsistent data distribution across clients, serving as an indicator of the data inconsistency among different hardware (e.g., coded apertures). Extensive experimental results demonstrate that the proposed FedHP coordinates the pre-trained model to multiple hardware configurations, outperforming prevalent FL frameworks for 0.35dB under challenging heterogeneous settings. Moreover, a Snapshot Spectral Heterogeneous Dataset has been built upon multiple practical SCI systems. Data and code are aveilable at https://github.com/Jiamian-Wang/FedHP-Snapshot-Compressive-Imaging

Jiamian Wang, Huan Wang, Yulun Zhang et al.

Image super-resolution (SR) has witnessed extensive neural network designs from CNN to transformer architectures. However, prevailing SR models suffer from prohibitive memory footprint and intensive computations, which limits further deployment on edge devices. This work investigates the potential of network pruning for super-resolution to take advantage of off-the-shelf network designs and reduce the underlying computational overhead. Two main challenges remain in applying pruning methods for SR. First, the widely-used filter pruning technique reflects limited granularity and restricted adaptability to diverse network structures. Second, existing pruning methods generally operate upon a pre-trained network for the sparse structure determination, hard to get rid of dense model training in the traditional SR paradigm. To address these challenges, we adopt unstructured pruning with sparse models directly trained from scratch. Specifically, we propose a novel Iterative Soft Shrinkage-Percentage (ISS-P) method by optimizing the sparse structure of a randomly initialized network at each iteration and tweaking unimportant weights with a small amount proportional to the magnitude scale on-the-fly. We observe that the proposed ISS-P can dynamically learn sparse structures adapting to the optimization process and preserve the sparse model's trainability by yielding a more regularized gradient throughput. Experiments on benchmark datasets demonstrate the effectiveness of the proposed ISS-P over diverse network architectures. Code is available at https://github.com/Jiamian-Wang/Iterative-Soft-Shrinkage-SR

Prasanna Reddy Pulakurthi, Jiamian Wang, Majid Rabbani et al.

Prevalent text-to-video retrieval systems mainly adopt embedding models for feature extraction and compute cosine similarities for ranking. However, this design presents two limitations. Low-quality text-video data pairs could compromise the retrieval, yet are hard to identify and examine. Cosine similarity alone provides no explanation for the ranking results, limiting the interpretability. We ask that can we interpret the ranking results, so as to assess the retrieval models and examine the text-video data? This work proposes X-CoT, an explainable retrieval framework upon LLM CoT reasoning in place of the embedding model-based similarity ranking. We first expand the existing benchmarks with additional video annotations to support semantic understanding and reduce data bias. We also devise a retrieval CoT consisting of pairwise comparison steps, yielding detailed reasoning and complete ranking. X-CoT empirically improves the retrieval performance and produces detailed rationales. It also facilitates the model behavior and data quality analysis. Code and data are available at: https://github.com/PrasannaPulakurthi/X-CoT.

Jiamian Wang, Yulun Zhang, Xin Yuan et al.

Recently, hyperspectral imaging (HSI) has attracted increasing research attention, especially for the ones based on a coded aperture snapshot spectral imaging (CASSI) system. Existing deep HSI reconstruction models are generally trained on paired data to retrieve original signals upon 2D compressed measurements given by a particular optical hardware mask in CASSI, during which the mask largely impacts the reconstruction performance and could work as a "model hyperparameter" governing on data augmentations. This mask-specific training style will lead to a hardware miscalibration issue, which sets up barriers to deploying deep HSI models among different hardware and noisy environments. To address this challenge, we introduce mask uncertainty for HSI with a complete variational Bayesian learning treatment and explicitly model it through a mask decomposition inspired by real hardware. Specifically, we propose a novel Graph-based Self-Tuning (GST) network to reason uncertainties adapting to varying spatial structures of masks among different hardware. Moreover, we develop a bilevel optimization framework to balance HSI reconstruction and uncertainty estimation, accounting for the hyperparameter property of masks. Extensive experimental results and model discussions validate the effectiveness (over 33/30 dB) of the proposed GST method under two miscalibration scenarios and demonstrate a highly competitive performance compared with the state-of-the-art well-calibrated methods. Our code and pre-trained model are available at https://github.com/Jiamian-Wang/mask_uncertainty_spectral_SCI

Jiamian Wang, Guohao Sun, Pichao Wang et al.

The increasing prevalence of video clips has sparked growing interest in text-video retrieval. Recent advances focus on establishing a joint embedding space for text and video, relying on consistent embedding representations to compute similarity. However, the text content in existing datasets is generally short and concise, making it hard to fully describe the redundant semantics of a video. Correspondingly, a single text embedding may be less expressive to capture the video embedding and empower the retrieval. In this study, we propose a new stochastic text modeling method T-MASS, i.e., text is modeled as a stochastic embedding, to enrich text embedding with a flexible and resilient semantic range, yielding a text mass. To be specific, we introduce a similarity-aware radius module to adapt the scale of the text mass upon the given text-video pairs. Plus, we design and develop a support text regularization to further control the text mass during the training. The inference pipeline is also tailored to fully exploit the text mass for accurate retrieval. Empirical evidence suggests that T-MASS not only effectively attracts relevant text-video pairs while distancing irrelevant ones, but also enables the determination of precise text embeddings for relevant pairs. Our experimental results show a substantial improvement of T-MASS over baseline (3% to 6.3% by R@1). Also, T-MASS achieves state-of-the-art performance on five benchmark datasets, including MSRVTT, LSMDC, DiDeMo, VATEX, and Charades.

Guohao Sun, Can Qin, Jiamian Wang et al.

Recent advances in vision-language models have shown notable generalization in broad tasks through visual instruction tuning. However, bridging the gap between the pre-trained vision encoder and the large language models (LLMs) becomes the whole network's bottleneck. To improve cross-modality alignment, existing works usually consider more visual instruction data covering a broader range of vision tasks to fine-tune the model for question-answering, which, however, is costly to obtain and has not thoroughly explored the rich contextual information contained in images. This paper first attempts to harness the overlooked context within visual instruction data, training the model to self-supervised "learning" how to ask high-quality questions. In this way, we introduce a novel framework named SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant. SQ-LLaVA exhibits proficiency in generating flexible and meaningful image-related questions while analyzing the visual clue and prior language knowledge, signifying an advanced level of generalized visual understanding. Moreover, fine-tuning SQ-LLaVA on higher-quality instruction data shows a performance improvement compared with traditional visual-instruction tuning methods. This improvement highlights the efficacy of self-questioning techniques in achieving a deeper and more nuanced comprehension of visual content across various contexts.

Jiamian Wang, Ziqi Zhou, Chaithanya Kumar Mummadi et al.

Autoregressive models excel in sequential modeling and have proven to be effective for vision-language data. However, the spatial nature of visual signals conflicts with the sequential dependencies of next-token prediction, leading to suboptimal results. This work proposes a plug-and-play refinement module to enhance the complex spatial correspondence modeling within the generated visual sequence. This module operates as a post-pretraining step to jointly refine all generated tokens of autoregressive model, enhancing vision-language modeling under a shared sequential prediction framework. By leveraging global context and relationship across the tokens, our method mitigates the error accumulation issue within the sequential generation. Experiments demonstrate that the proposed method improves the generation quality, enhancing the model's ability to produce semantically consistent results.

Jiamian Wang, Kunpeng Li, Yulun Zhang et al.

Snapshot compressive imaging (SCI) surges as a novel way of capturing hyperspectral images. It operates an optical encoder to compress the 3D data into a 2D measurement and adopts a software decoder for the signal reconstruction. Recently, a representative SCI set-up of coded aperture snapshot compressive imager (CASSI) with Transformer reconstruction backend remarks high-fidelity sensing performance. However, dominant spatial and spectral attention designs show limitations in hyperspectral modeling. The spatial attention values describe the inter-pixel correlation but overlook the across-spectra variation within each pixel. The spectral attention size is unscalable to the token spatial size and thus bottlenecks information allocation. Besides, CASSI entangles the spatial and spectral information into a 2D measurement, placing a barrier for information disentanglement and modeling. In addition, CASSI blocks the light with a physical binary mask, yielding the masked data loss. To tackle above challenges, we propose a spatial-spectral (S2-) Transformer implemented by a paralleled attention design and a mask-aware learning strategy. Firstly, we systematically explore pros and cons of different spatial (-spectral) attention designs, based on which we find performing both attentions in parallel well disentangles and models the blended information. Secondly, the masked pixels induce higher prediction difficulty and should be treated differently from unmasked ones. We adaptively prioritize the loss penalty attributing to the mask structure by referring to the mask-encoded prediction as an uncertainty estimator. We theoretically discuss the distinct convergence tendencies between masked/unmasked regions of the proposed learning strategy. Extensive experiments demonstrate that on average, the results of the proposed method are superior over the state-of-the-art method.

Jiamian Wang, Yulun Zhang, Xin Yuan et al.

The emerging technology of snapshot compressive imaging (SCI) enables capturing high dimensional (HD) data in an efficient way. It is generally implemented by two components: an optical encoder that compresses HD signals into a 2D measurement and an algorithm decoder that retrieves the HD data upon the hardware-encoded measurement. Over a broad range of SCI applications, hyperspectral imaging (HSI) and video compressive sensing have received significant research attention in recent years. Among existing SCI reconstruction algorithms, deep learning-based methods stand out as their promising performance and efficient inference. However, the deep reconstruction network may suffer from overlarge model size and highly-specialized network design, which inevitably lead to costly training time, high memory usage, and limited flexibility, thus discouraging the deployments of SCI systems in practical scenarios. In this paper, we tackle the above challenges by proposing a simple yet highly efficient reconstruction method, namely stacked residual network (SRN), by revisiting the residual learning strategy with nested structures and spatial-invariant property. The proposed SRN empowers high-fidelity data retrieval with fewer computation operations and negligible model size compared with existing networks, and also serves as a versatile backbone applicable for both hyperspectral and video data. Based on the proposed backbone, we first develop the channel attention enhanced SRN (CAE-SRN) to explore the spectral inter-dependencies for fine-grained spatial estimation in HSI. We then employ SRN as a deep denoiser and incorporate it into a generalized alternating projection (GAP) framework -- resulting in GAP-SRN -- to handle the video compressive sensing task. Experimental results demonstrate the state-of-the-art performance, high computational efficiency of the proposed SRN on two SCI applications.

Aristotelis-Angelos Papadopoulos, Mohammad Reza Rajati, Nazim Shaikh et al.

Deep neural networks have achieved great success in classification tasks during the last years. However, one major problem to the path towards artificial intelligence is the inability of neural networks to accurately detect samples from novel class distributions and therefore, most of the existent classification algorithms assume that all classes are known prior to the training stage. In this work, we propose a methodology for training a neural network that allows it to efficiently detect out-of-distribution (OOD) examples without compromising much of its classification accuracy on the test examples from known classes. We propose a novel loss function that gives rise to a novel method, Outlier Exposure with Confidence Control (OECC), which achieves superior results in OOD detection with OE both on image and text classification tasks without requiring access to OOD samples. Additionally, we experimentally show that the combination of OECC with state-of-the-art post-training OOD detection methods, like the Mahalanobis Detector (MD) and the Gramian Matrices (GM) methods, further improves their performance in the OOD detection task, demonstrating the potential of combining training and post-training methods for OOD detection.