Towards Debiasing Frame Length Bias in Text-Video Retrieval via Causal Intervention

Many studies focus on improving pretraining or developing new backbones in text-video retrieval. However, existing methods may suffer from the learning and inference bias issue, as recent research suggests in other text-video-related tasks. For instance, spatial appearance features on action recognition or temporal object co-occurrences on video scene graph generation could induce spurious correlations. In this work, we present a unique and systematic study of a temporal bias due to frame length discrepancy between training and test sets of trimmed video clips, which is the first such attempt for a text-video retrieval task, to the best of our knowledge. We first hypothesise and verify the bias on how it would affect the model illustrated with a baseline study. Then, we propose a causal debiasing approach and perform extensive experiments and ablation studies on the Epic-Kitchens-100, YouCook2, and MSR-VTT datasets. Our model overpasses the baseline and SOTA on nDCG, a semantic-relevancy-focused evaluation metric which proves the bias is mitigated, as well as on the other conventional metrics.

Empowering Dynamics-aware Text-to-Video Diffusion with Large Language Models

Text-to-video (T2V) synthesis has gained increasing attention in the community, in which the recently emerged diffusion models (DMs) have promisingly shown stronger performance than the past approaches. While existing state-of-the-art DMs are competent to achieve high-resolution video generation, they may largely suffer from key limitations (e.g., action occurrence disorders, crude video motions) with respect to the intricate temporal dynamics modeling, one of the crux of video synthesis. In this work, we investigate strengthening the awareness of video dynamics for DMs, for high-quality T2V generation. Inspired by human intuition, we design an innovative dynamic scene manager (dubbed as Dysen) module, which includes (step-1) extracting from input text the key actions with proper time-order arrangement, (step-2) transforming the action schedules into the dynamic scene graph (DSG) representations, and (step-3) enriching the scenes in the DSG with sufficient and reasonable details. Taking advantage of the existing powerful LLMs (e.g., ChatGPT) via in-context learning, Dysen realizes (nearly) human-level temporal dynamics understanding. Finally, the resulting video DSG with rich action scene details is encoded as fine-grained spatio-temporal features, integrated into the backbone T2V DM for video generating. Experiments on popular T2V datasets suggest that our framework consistently outperforms prior arts with significant margins, especially in the scenario with complex actions. Project page at https://haofei.vip/Dysen-VDM

Invariant Training 2D-3D Joint Hard Samples for Few-Shot Point Cloud Recognition

We tackle the data scarcity challenge in few-shot point cloud recognition of 3D objects by using a joint prediction from a conventional 3D model and a well-trained 2D model. Surprisingly, such an ensemble, though seems trivial, has hardly been shown effective in recent 2D-3D models. We find out the crux is the less effective training for the ''joint hard samples'', which have high confidence prediction on different wrong labels, implying that the 2D and 3D models do not collaborate well. To this end, our proposed invariant training strategy, called InvJoint, does not only emphasize the training more on the hard samples, but also seeks the invariance between the conflicting 2D and 3D ambiguous predictions. InvJoint can learn more collaborative 2D and 3D representations for better ensemble. Extensive experiments on 3D shape classification with widely adopted ModelNet10/40, ScanObjectNN and Toys4K, and shape retrieval with ShapeNet-Core validate the superiority of our InvJoint.

Empowering Vision-Language Models to Follow Interleaved Vision-Language Instructions

Multimodal Large Language Models (MLLMs) have recently sparked significant interest, which demonstrates emergent capabilities to serve as a general-purpose model for various vision-language tasks. However, existing methods mainly focus on limited types of instructions with a single image as visual context, which hinders the widespread availability of MLLMs. In this paper, we introduce the I4 benchmark to comprehensively evaluate the instruction following ability on complicated interleaved vision-language instructions, which involve intricate image-text sequential context, covering a diverse range of scenarios (e.g., visually-rich webpages/textbooks, lecture slides, embodied dialogue). Systematic evaluation on our I4 benchmark reveals a common defect of existing methods: the Visual Prompt Generator (VPG) trained on image-captioning alignment objective tends to attend to common foreground information for captioning but struggles to extract specific information required by particular tasks. To address this issue, we propose a generic and lightweight controllable knowledge re-injection module, which utilizes the sophisticated reasoning ability of LLMs to control the VPG to conditionally extract instruction-specific visual information and re-inject it into the LLM. Further, we introduce an annotation-free cross-attention guided counterfactual image training strategy to methodically learn the proposed module by collaborating a cascade of foundation models. Enhanced by the proposed module and training strategy, we present Cheetor, a Transformer-based MLLM that can effectively handle a wide variety of interleaved vision-language instructions and achieves state-of-the-art zero-shot performance across all tasks of I4, without high-quality multimodal instruction tuning data. Cheetor also exhibits competitive performance compared with state-of-the-art instruction tuned models on MME benchmark.

Random Boxes Are Open-world Object Detectors

We show that classifiers trained with random region proposals achieve state-of-the-art Open-world Object Detection (OWOD): they can not only maintain the accuracy of the known objects (w/ training labels), but also considerably improve the recall of unknown ones (w/o training labels). Specifically, we propose RandBox, a Fast R-CNN based architecture trained on random proposals at each training iteration, surpassing existing Faster R-CNN and Transformer based OWOD. Its effectiveness stems from the following two benefits introduced by randomness. First, as the randomization is independent of the distribution of the limited known objects, the random proposals become the instrumental variable that prevents the training from being confounded by the known objects. Second, the unbiased training encourages more proposal explorations by using our proposed matching score that does not penalize the random proposals whose prediction scores do not match the known objects. On two benchmarks: Pascal-VOC/MS-COCO and LVIS, RandBox significantly outperforms the previous state-of-the-art in all metrics. We also detail the ablations on randomization and loss designs. Codes are available at https://github.com/scuwyh2000/RandBox.

DisCo: Disentangled Control for Referring Human Dance Generation in Real World

Generative AI has made significant strides in computer vision, particularly in image/video synthesis conditioned on text descriptions. Despite the advancements, it remains challenging especially in the generation of human-centric content such as dance synthesis. Existing dance synthesis methods struggle with the gap between synthesized content and real-world dance scenarios. In this paper, we define a new problem setting: Referring Human Dance Generation, which focuses on real-world dance scenarios with three important properties: (i) Faithfulness: the synthesis should retain the appearance of both human subject foreground and background from the reference image, and precisely follow the target pose; (ii) Generalizability: the model should generalize to unseen human subjects, backgrounds, and poses; (iii) Compositionality: it should allow for composition of seen/unseen subjects, backgrounds, and poses from different sources. To address these challenges, we introduce a novel approach, DISCO, which includes a novel model architecture with disentangled control to improve the faithfulness and compositionality of dance synthesis, and an effective human attribute pre-training for better generalizability to unseen humans. Extensive qualitative and quantitative results demonstrate that DISCO can generate high-quality human dance images and videos with diverse appearances and flexible motions. Code, demo, video and visualization are available at: https://disco-dance.github.io/.

Fast Diffusion Model

Despite their success in real data synthesis, diffusion models (DMs) often suffer from slow and costly training and sampling issues, limiting their broader applications. To mitigate this, we propose a Fast Diffusion Model (FDM) which improves the diffusion process of DMs from a stochastic optimization perspective to speed up both training and sampling. Specifically, we first find that the diffusion process of DMs accords with the stochastic optimization process of stochastic gradient descent (SGD) on a stochastic time-variant problem. Note that momentum SGD uses both the current gradient and an extra momentum, achieving more stable and faster convergence. We are inspired to introduce momentum into the diffusion process to accelerate both training and sampling. However, this comes with the challenge of deriving the noise perturbation kernel from the momentum-based diffusion process. To this end, we frame the momentum-based process as a Damped Oscillation system whose critically damped state -- the kernel solution -- avoids oscillation and thus has a faster convergence speed of the diffusion process. Empirical results show that our FDM can be applied to several popular DM frameworks, e.g. VP, VE, and EDM, and reduces their training cost by about 50% with comparable image synthesis performance on CIFAR-10, FFHQ, and AFHQv2 datasets. Moreover, FDM decreases their sampling steps by about $3\times$ to achieve similar performance under the same deterministic samplers. The code is available at https://github.com/sail-sg/FDM.

An Overview of Challenges in Egocentric Text-Video Retrieval

Text-video retrieval contains various challenges, including biases coming from diverse sources. We highlight some of them supported by illustrations to open a discussion. Besides, we address one of the biases, frame length bias, with a simple method which brings a very incremental but promising increase. We conclude with future directions.

Decoupled Kullback-Leibler Divergence Loss

In this paper, we delve deeper into the Kullback-Leibler (KL) Divergence loss and observe that it is equivalent to the Doupled Kullback-Leibler (DKL) Divergence loss that consists of 1) a weighted Mean Square Error (wMSE) loss and 2) a Cross-Entropy loss incorporating soft labels. From our analysis of the DKL loss, we have identified two areas for improvement. Firstly, we address the limitation of DKL in scenarios like knowledge distillation by breaking its asymmetry property in training optimization. This modification ensures that the wMSE component is always effective during training, providing extra constructive cues. Secondly, we introduce global information into DKL for intra-class consistency regularization. With these two enhancements, we derive the Improved Kullback-Leibler (IKL) Divergence loss and evaluate its effectiveness by conducting experiments on CIFAR-10/100 and ImageNet datasets, focusing on adversarial training and knowledge distillation tasks. The proposed approach achieves new state-of-the-art performance on both tasks, demonstrating the substantial practical merits. Code and models will be available soon at https://github.com/jiequancui/DKL.

Equivariant Similarity for Vision-Language Foundation Models

This study explores the concept of equivariance in vision-language foundation models (VLMs), focusing specifically on the multimodal similarity function that is not only the major training objective but also the core delivery to support downstream tasks. Unlike the existing image-text similarity objective which only categorizes matched pairs as similar and unmatched pairs as dissimilar, equivariance also requires similarity to vary faithfully according to the semantic changes. This allows VLMs to generalize better to nuanced and unseen multimodal compositions. However, modeling equivariance is challenging as the ground truth of semantic change is difficult to collect. For example, given an image-text pair about a dog, it is unclear to what extent the similarity changes when the pixel is changed from dog to cat? To this end, we propose EqSim, a regularization loss that can be efficiently calculated from any two matched training pairs and easily pluggable into existing image-text retrieval fine-tuning. Meanwhile, to further diagnose the equivariance of VLMs, we present a new challenging benchmark EqBen. Compared to the existing evaluation sets, EqBen is the first to focus on "visual-minimal change". Extensive experiments show the lack of equivariance in current VLMs and validate the effectiveness of EqSim. Code is available at \url{https://github.com/Wangt-CN/EqBen}.