Principles of Visual Tokens for Efficient Video Understanding

Video understanding has made huge strides in recent years, relying largely on the power of the transformer architecture. As this architecture is notoriously expensive and video is highly redundant, research into improving efficiency has become particularly relevant. This has led to many creative solutions, including token merging and token selection. While most methods succeed in reducing the cost of the model and maintaining accuracy, an interesting pattern arises: most methods do not outperform the random sampling baseline. In this paper we take a closer look at this phenomenon and make several observations. First, we develop an oracle for the value of tokens which exposes a clear Pareto distribution where most tokens have remarkably low value, and just a few carry most of the perceptual information. Second, we analyze why this oracle is extremely hard to learn, as it does not consistently coincide with visual cues. Third, we observe that easy videos need fewer tokens to maintain accuracy. We build on these and further insights to propose a lightweight video model we call LITE that can select a small number of tokens effectively, outperforming state-of-the-art and existing baselines across datasets (Kinetics400 and Something-Something-V2) in the challenging trade-off of computation (GFLOPs) vs accuracy.

Towards Optimal Adapter Placement for Efficient Transfer Learning

Parameter-efficient transfer learning (PETL) aims to adapt pre-trained models to new downstream tasks while minimizing the number of fine-tuned parameters. Adapters, a popular approach in PETL, inject additional capacity into existing networks by incorporating low-rank projections, achieving performance comparable to full fine-tuning with significantly fewer parameters. This paper investigates the relationship between the placement of an adapter and its performance. We observe that adapter location within a network significantly impacts its effectiveness, and that the optimal placement is task-dependent. To exploit this observation, we introduce an extended search space of adapter connections, including long-range and recurrent adapters. We demonstrate that even randomly selected adapter placements from this expanded space yield improved results, and that high-performing placements often correlate with high gradient rank. Our findings reveal that a small number of strategically placed adapters can match or exceed the performance of the common baseline of adding adapters in every block, opening a new avenue for research into optimal adapter placement strategies.

Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels

Large-scale vision-language models like CLIP have demonstrated impressive open-vocabulary capabilities for image-level tasks, excelling in recognizing what objects are present. However, they struggle with pixel-level recognition tasks like semantic segmentation, which additionally require understanding where the objects are located. In this work, we propose a novel method, PixelCLIP, to adapt the CLIP image encoder for pixel-level understanding by guiding the model on where, which is achieved using unlabeled images and masks generated from vision foundation models such as SAM and DINO. To address the challenges of leveraging masks without semantic labels, we devise an online clustering algorithm using learnable class names to acquire general semantic concepts. PixelCLIP shows significant performance improvements over CLIP and competitive results compared to caption-supervised methods in open-vocabulary semantic segmentation. Project page is available at https://cvlab-kaist.github.io/PixelCLIP

Mixture of Nested Experts: Adaptive Processing of Visual Tokens

The visual medium (images and videos) naturally contains a large amount of information redundancy, thereby providing a great opportunity for leveraging efficiency in processing. While Vision Transformer (ViT) based models scale effectively to large data regimes, they fail to capitalize on this inherent redundancy, leading to higher computational costs. Mixture of Experts (MoE) networks demonstrate scalability while maintaining same inference-time costs, but they come with a larger parameter footprint. We present Mixture of Nested Experts (MoNE), which utilizes a nested structure for experts, wherein individual experts fall on an increasing compute-accuracy curve. Given a compute budget, MoNE learns to dynamically choose tokens in a priority order, and thus redundant tokens are processed through cheaper nested experts. Using this framework, we achieve equivalent performance as the baseline models, while reducing inference time compute by over two-fold. We validate our approach on standard image and video datasets - ImageNet-21K, Kinetics400, and Something-Something-v2. We further highlight MoNE$'$s adaptability by showcasing its ability to maintain strong performance across different inference-time compute budgets on videos, using only a single trained model.

Streaming Dense Video Captioning

An ideal model for dense video captioning -- predicting captions localized temporally in a video -- should be able to handle long input videos, predict rich, detailed textual descriptions, and be able to produce outputs before processing the entire video. Current state-of-the-art models, however, process a fixed number of downsampled frames, and make a single full prediction after seeing the whole video. We propose a streaming dense video captioning model that consists of two novel components: First, we propose a new memory module, based on clustering incoming tokens, which can handle arbitrarily long videos as the memory is of a fixed size. Second, we develop a streaming decoding algorithm that enables our model to make predictions before the entire video has been processed. Our model achieves this streaming ability, and significantly improves the state-of-the-art on three dense video captioning benchmarks: ActivityNet, YouCook2 and ViTT. Our code is released at https://github.com/google-research/scenic.

Time-, Memory- and Parameter-Efficient Visual Adaptation

As foundation models become more popular, there is a growing need to efficiently finetune them for downstream tasks. Although numerous adaptation methods have been proposed, they are designed to be efficient only in terms of how many parameters are trained. They, however, typically still require backpropagating gradients throughout the model, meaning that their training-time and -memory cost does not reduce as significantly. We propose an adaptation method which does not backpropagate gradients through the backbone. We achieve this by designing a lightweight network in parallel that operates on features from the frozen, pretrained backbone. As a result, our method is efficient not only in terms of parameters, but also in training-time and memory usage. Our approach achieves state-of-the-art accuracy-parameter trade-offs on the popular VTAB benchmark, and we further show how we outperform prior works with respect to training-time and -memory usage too. We further demonstrate the training efficiency and scalability of our method by adapting a vision transformer backbone of 4 billion parameters for the computationally demanding task of video classification, without any intricate model parallelism. Here, we outperform a prior adaptor-based method which could only scale to a 1 billion parameter backbone, or fully-finetuning a smaller backbone, with the same GPU and less training time.

Pixel Aligned Language Models

Large language models have achieved great success in recent years, so as their variants in vision. Existing vision-language models can describe images in natural languages, answer visual-related questions, or perform complex reasoning about the image. However, it is yet unclear how localization tasks, such as word grounding or referring localization, can be performed using large language models. In this work, we aim to develop a vision-language model that can take locations, for example, a set of points or boxes, as either inputs or outputs. When taking locations as inputs, the model performs location-conditioned captioning, which generates captions for the indicated object or region. When generating locations as outputs, our model regresses pixel coordinates for each output word generated by the language model, and thus performs dense word grounding. Our model is pre-trained on the Localized Narrative dataset, which contains pixel-word-aligned captioning from human attention. We show our model can be applied to various location-aware vision-language tasks, including referring localization, location-conditioned captioning, and dense object captioning, archiving state-of-the-art performance on RefCOCO and Visual Genome. Project page: https://jerryxu.net/PixelLLM .

Video Summarization: Towards Entity-Aware Captions

Existing popular video captioning benchmarks and models deal with generic captions devoid of specific person, place or organization named entities. In contrast, news videos present a challenging setting where the caption requires such named entities for meaningful summarization. As such, we propose the task of summarizing news video directly to entity-aware captions. We also release a large-scale dataset, VIEWS (VIdeo NEWS), to support research on this task. Further, we propose a method that augments visual information from videos with context retrieved from external world knowledge to generate entity-aware captions. We demonstrate the effectiveness of our approach on three video captioning models. We also show that our approach generalizes to existing news image captions dataset. With all the extensive experiments and insights, we believe we establish a solid basis for future research on this challenging task.

UnLoc: A Unified Framework for Video Localization Tasks

While large-scale image-text pretrained models such as CLIP have been used for multiple video-level tasks on trimmed videos, their use for temporal localization in untrimmed videos is still a relatively unexplored task. We design a new approach for this called UnLoc, which uses pretrained image and text towers, and feeds tokens to a video-text fusion model. The output of the fusion module are then used to construct a feature pyramid in which each level connects to a head to predict a per-frame relevancy score and start/end time displacements. Unlike previous works, our architecture enables Moment Retrieval, Temporal Localization, and Action Segmentation with a single stage model, without the need for action proposals, motion based pretrained features or representation masking. Unlike specialized models, we achieve state of the art results on all three different localization tasks with a unified approach. Code will be available at: \url{https://github.com/google-research/scenic}.

Does Visual Pretraining Help End-to-End Reasoning?

We aim to investigate whether end-to-end learning of visual reasoning can be achieved with general-purpose neural networks, with the help of visual pretraining. A positive result would refute the common belief that explicit visual abstraction (e.g. object detection) is essential for compositional generalization on visual reasoning, and confirm the feasibility of a neural network "generalist" to solve visual recognition and reasoning tasks. We propose a simple and general self-supervised framework which "compresses" each video frame into a small set of tokens with a transformer network, and reconstructs the remaining frames based on the compressed temporal context. To minimize the reconstruction loss, the network must learn a compact representation for each image, as well as capture temporal dynamics and object permanence from temporal context. We perform evaluation on two visual reasoning benchmarks, CATER and ACRE. We observe that pretraining is essential to achieve compositional generalization for end-to-end visual reasoning. Our proposed framework outperforms traditional supervised pretraining, including image classification and explicit object detection, by large margins.