Beyond Raw Videos: Understanding Edited Videos with Large Multimodal Model

The emerging video LMMs (Large Multimodal Models) have achieved significant improvements on generic video understanding in the form of VQA (Visual Question Answering), where the raw videos are captured by cameras. However, a large portion of videos in real-world applications are edited videos, \textit{e.g.}, users usually cut and add effects/modifications to the raw video before publishing it on social media platforms. The edited videos usually have high view counts but they are not covered in existing benchmarks of video LMMs, \textit{i.e.}, ActivityNet-QA, or VideoChatGPT benchmark. In this paper, we leverage the edited videos on a popular short video platform, \textit{i.e.}, TikTok, and build a video VQA benchmark (named EditVid-QA) covering four typical editing categories, i.e., effect, funny, meme, and game. Funny and meme videos benchmark nuanced understanding and high-level reasoning, while effect and game evaluate the understanding capability of artificial design. Most of the open-source video LMMs perform poorly on the EditVid-QA benchmark, indicating a huge domain gap between edited short videos on social media and regular raw videos. To improve the generalization ability of LMMs, we collect a training set for the proposed benchmark based on both Panda-70M/WebVid raw videos and small-scale TikTok/CapCut edited videos, which boosts the performance on the proposed EditVid-QA benchmark, indicating the effectiveness of high-quality training data. We also identified a serious issue in the existing evaluation protocol using the GPT-3.5 judge, namely a "sorry" attack, where a sorry-style naive answer can achieve an extremely high rating from the GPT judge, e.g., over 4.3 for correctness score on VideoChatGPT evaluation protocol. To avoid the "sorry" attacks, we evaluate results with GPT-4 judge and keyword filtering. The datasets will be released for academic purposes only.

CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts

Recent advancements in Multimodal Large Language Models (LLMs) have focused primarily on scaling by increasing text-image pair data and enhancing LLMs to improve performance on multimodal tasks. However, these scaling approaches are computationally expensive and overlook the significance of improving model capabilities from the vision side. Inspired by the successful applications of Mixture-of-Experts (MoE) in LLMs, which improves model scalability during training while keeping inference costs similar to those of smaller models, we propose CuMo. CuMo incorporates Co-upcycled Top-K sparsely-gated Mixture-of-experts blocks into both the vision encoder and the MLP connector, thereby enhancing the multimodal LLMs with minimal additional activated parameters during inference. CuMo first pre-trains the MLP blocks and then initializes each expert in the MoE block from the pre-trained MLP block during the visual instruction tuning stage. Auxiliary losses are used to ensure a balanced loading of experts. CuMo outperforms state-of-the-art multimodal LLMs across various VQA and visual-instruction-following benchmarks using models within each model size group, all while training exclusively on open-sourced datasets. The code and model weights for CuMo are open-sourced at https://github.com/SHI-Labs/CuMo.

HAAV: Hierarchical Aggregation of Augmented Views for Image Captioning

A great deal of progress has been made in image captioning, driven by research into how to encode the image using pre-trained models. This includes visual encodings (e.g. image grid features or detected objects) and more recently textual encodings (e.g. image tags or text descriptions of image regions). As more advanced encodings are available and incorporated, it is natural to ask: how to efficiently and effectively leverage the heterogeneous set of encodings? In this paper, we propose to regard the encodings as augmented views of the input image. The image captioning model encodes each view independently with a shared encoder efficiently, and a contrastive loss is incorporated across the encoded views in a novel way to improve their representation quality and the model's data efficiency. Our proposed hierarchical decoder then adaptively weighs the encoded views according to their effectiveness for caption generation by first aggregating within each view at the token level, and then across views at the view level. We demonstrate significant performance improvements of +5.6% CIDEr on MS-COCO and +12.9% CIDEr on Flickr30k compared to state of the arts, and conduct rigorous analyses to demonstrate the importance of each part of our design.

CLIP-GCD: Simple Language Guided Generalized Category Discovery

Generalized Category Discovery (GCD) requires a model to both classify known categories and cluster unknown categories in unlabeled data. Prior methods leveraged self-supervised pre-training combined with supervised fine-tuning on the labeled data, followed by simple clustering methods. In this paper, we posit that such methods are still prone to poor performance on out-of-distribution categories, and do not leverage a key ingredient: Semantic relationships between object categories. We therefore propose to leverage multi-modal (vision and language) models, in two complementary ways. First, we establish a strong baseline by replacing uni-modal features with CLIP, inspired by its zero-shot performance. Second, we propose a novel retrieval-based mechanism that leverages CLIP's aligned vision-language representations by mining text descriptions from a text corpus for the labeled and unlabeled set. We specifically use the alignment between CLIP's visual encoding of the image and textual encoding of the corpus to retrieve top-k relevant pieces of text and incorporate their embeddings to perform joint image+text semi-supervised clustering. We perform rigorous experimentation and ablations (including on where to retrieve from, how much to retrieve, and how to combine information), and validate our results on several datasets including out-of-distribution domains, demonstrating state-of-art results.

Structure-Encoding Auxiliary Tasks for Improved Visual Representation in Vision-and-Language Navigation

In Vision-and-Language Navigation (VLN), researchers typically take an image encoder pre-trained on ImageNet without fine-tuning on the environments that the agent will be trained or tested on. However, the distribution shift between the training images from ImageNet and the views in the navigation environments may render the ImageNet pre-trained image encoder suboptimal. Therefore, in this paper, we design a set of structure-encoding auxiliary tasks (SEA) that leverage the data in the navigation environments to pre-train and improve the image encoder. Specifically, we design and customize (1) 3D jigsaw, (2) traversability prediction, and (3) instance classification to pre-train the image encoder. Through rigorous ablations, our SEA pre-trained features are shown to better encode structural information of the scenes, which ImageNet pre-trained features fail to properly encode but is crucial for the target navigation task. The SEA pre-trained features can be easily plugged into existing VLN agents without any tuning. For example, on Test-Unseen environments, the VLN agents combined with our SEA pre-trained features achieve absolute success rate improvement of 12% for Speaker-Follower, 5% for Env-Dropout, and 4% for AuxRN.

Beyond a Pre-Trained Object Detector: Cross-Modal Textual and Visual Context for Image Captioning

Significant progress has been made on visual captioning, largely relying on pre-trained features and later fixed object detectors that serve as rich inputs to auto-regressive models. A key limitation of such methods, however, is that the output of the model is conditioned only on the object detector's outputs. The assumption that such outputs can represent all necessary information is unrealistic, especially when the detector is transferred across datasets. In this work, we reason about the graphical model induced by this assumption, and propose to add an auxiliary input to represent missing information such as object relationships. We specifically propose to mine attributes and relationships from the Visual Genome dataset and condition the captioning model on them. Crucially, we propose (and show to be important) the use of a multi-modal pre-trained model (CLIP) to retrieve such contextual descriptions. Further, object detector models are frozen and do not have sufficient richness to allow the captioning model to properly ground them. As a result, we propose to condition both the detector and description outputs on the image, and show qualitatively and quantitatively that this can improve grounding. We validate our method on image captioning, perform thorough analyses of each component and importance of the pre-trained multi-modal model, and demonstrate significant improvements over the current state of the art, specifically +7.5% in CIDEr and +1.3% in BLEU-4 metrics.

Unbiased Teacher for Semi-Supervised Object Detection

Semi-supervised learning, i.e., training networks with both labeled and unlabeled data, has made significant progress recently. However, existing works have primarily focused on image classification tasks and neglected object detection which requires more annotation effort. In this work, we revisit the Semi-Supervised Object Detection (SS-OD) and identify the pseudo-labeling bias issue in SS-OD. To address this, we introduce Unbiased Teacher, a simple yet effective approach that jointly trains a student and a gradually progressing teacher in a mutually-beneficial manner. Together with a class-balance loss to downweight overly confident pseudo-labels, Unbiased Teacher consistently improved state-of-the-art methods by significant margins on COCO-standard, COCO-additional, and VOC datasets. Specifically, Unbiased Teacher achieves 6.8 absolute mAP improvements against state-of-the-art method when using 1% of labeled data on MS-COCO, achieves around 10 mAP improvements against the supervised baseline when using only 0.5, 1, 2% of labeled data on MS-COCO.

FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning

Recent state-of-the-art semi-supervised learning (SSL) methods use a combination of image-based transformations and consistency regularization as core components. Such methods, however, are limited to simple transformations such as traditional data augmentation or convex combinations of two images. In this paper, we propose a novel learned feature-based refinement and augmentation method that produces a varied set of complex transformations. Importantly, these transformations also use information from both within-class and across-class prototypical representations that we extract through clustering. We use features already computed across iterations by storing them in a memory bank, obviating the need for significant extra computation. These transformations, combined with traditional image-based augmentation, are then used as part of the consistency-based regularization loss. We demonstrate that our method is comparable to current state of art for smaller datasets (CIFAR-10 and SVHN) while being able to scale up to larger datasets such as CIFAR-100 and mini-Imagenet where we achieve significant gains over the state of art (\textit{e.g.,} absolute 17.44\% gain on mini-ImageNet). We further test our method on DomainNet, demonstrating better robustness to out-of-domain unlabeled data, and perform rigorous ablations and analysis to validate the method.

Who2com: Collaborative Perception via Learnable Handshake Communication

In this paper, we propose the problem of collaborative perception, where robots can combine their local observations with those of neighboring agents in a learnable way to improve accuracy on a perception task. Unlike existing work in robotics and multi-agent reinforcement learning, we formulate the problem as one where learned information must be shared across a set of agents in a bandwidth-sensitive manner to optimize for scene understanding tasks such as semantic segmentation. Inspired by networking communication protocols, we propose a multi-stage handshake communication mechanism where the neural network can learn to compress relevant information needed for each stage. Specifically, a target agent with degraded sensor data sends a compressed request, the other agents respond with matching scores, and the target agent determines who to connect with (i.e., receive information from). We additionally develop the AirSim-CP dataset and metrics based on the AirSim simulator where a group of aerial robots perceive diverse landscapes, such as roads, grasslands, buildings, etc. We show that for the semantic segmentation task, our handshake communication method significantly improves accuracy by approximately 20% over decentralized baselines, and is comparable to centralized ones using a quarter of the bandwidth.

Manifold Graph with Learned Prototypes for Semi-Supervised Image Classification

Recent advances in semi-supervised learning methods rely on estimating the categories of unlabeled data using a model trained on the labeled data (pseudo-labeling) and using the unlabeled data for various consistency-based regularization. In this work, we propose to explicitly leverage the structure of the data manifold based on a Manifold Graph constructed over the image instances within the feature space. Specifically, we propose an architecture based on graph networks that jointly optimizes feature extraction, graph connectivity, and feature propagation and aggregation to unlabeled data in an end-to-end manner. Further, we present a novel Prototype Generator for producing a diverse set of prototypes that compactly represent each category, which supports feature propagation. To evaluate our method, we first contribute a strong baseline that combines two consistency-based regularizers that already achieves state-of-the-art results especially with fewer labels. We then show that when combined with these regularizers, the proposed method facilitates the propagation of information from generated prototypes to image data to further improve results. We provide extensive qualitative and quantitative experimental results on semi-supervised benchmarks demonstrating the improvements arising from our design and show that our method achieves state-of-the-art performance when compared with existing methods using a single model and comparable with ensemble methods. Specifically, we achieve error rates of 3.35% on SVHN, 8.27% on CIFAR-10, and 33.83% on CIFAR-100. With much fewer labels, we surpass the state of the arts by significant margins of 41% relative error decrease on average.