TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models

Recent advances in multimodal Large Language Models (LLMs) have shown great success in understanding multi-modal contents. For video understanding tasks, training-based video LLMs are difficult to build due to the scarcity of high-quality, curated video-text paired data. In contrast, paired image-text data are much easier to obtain, and there is substantial similarity between images and videos. Consequently, extending image LLMs for video understanding tasks presents an appealing alternative. Developing effective strategies for compressing visual tokens from multiple frames is a promising way to leverage the powerful pre-trained image LLM. In this work, we explore the limitations of the existing compression strategies for building a training-free video LLM. The findings lead to our method TS-LLaVA, which constructs visual tokens through a Thumbnail-and-Sampling strategy. Given a video, we select few equidistant frames from all input frames to construct a Thumbnail image as a detailed visual cue, complemented by Sampled visual tokens from all input frames. Our method establishes the new state-of-the-art performance among training-free video LLMs on various benchmarks. Notably, our 34B model outperforms GPT-4V on the MVBench benchmark, and achieves performance comparable to the 72B training-based video LLM, Video-LLaMA2, on the challenging MLVU benchmark. Code is available at https://github.com/tingyu215/TS-LLaVA.

Failure-Proof Non-Contrastive Self-Supervised Learning

We identify sufficient conditions to avoid known failure modes, including representation, dimensional, cluster and intracluster collapses, occurring in non-contrastive self-supervised learning. Based on these findings, we propose a principled design for the projector and loss function. We theoretically demonstrate that this design introduces an inductive bias that promotes learning representations that are both decorrelated and clustered without explicit enforcing these properties and leading to improved generalization. To the best of our knowledge, this is the first solution that achieves robust training with respect to these failure modes while guaranteeing enhanced generalization performance in downstream tasks. We validate our theoretical findings on image datasets including SVHN, CIFAR10, CIFAR100 and ImageNet-100, and show that our solution, dubbed FALCON, outperforms existing feature decorrelation and cluster-based self-supervised learning methods in terms of generalization to clustering and linear classification tasks.

Analysis of Spatial augmentation in Self-supervised models in the purview of training and test distributions

In this paper, we present an empirical study of typical spatial augmentation techniques used in self-supervised representation learning methods (both contrastive and non-contrastive), namely random crop and cutout. Our contributions are: (a) we dissociate random cropping into two separate augmentations, overlap and patch, and provide a detailed analysis on the effect of area of overlap and patch size to the accuracy on down stream tasks. (b) We offer an insight into why cutout augmentation does not learn good representation, as reported in earlier literature. Finally, based on these analysis, (c) we propose a distance-based margin to the invariance loss for learning scene-centric representations for the downstream task on object-centric distribution, showing that as simple as a margin proportional to the pixel distance between the two spatial views in the scence-centric images can improve the learned representation. Our study furthers the understanding of the spatial augmentations, and the effect of the domain-gap between the training augmentations and the test distribution.

Navigating the Nuances: A Fine-grained Evaluation of Vision-Language Navigation

This study presents a novel evaluation framework for the Vision-Language Navigation (VLN) task. It aims to diagnose current models for various instruction categories at a finer-grained level. The framework is structured around the context-free grammar (CFG) of the task. The CFG serves as the basis for the problem decomposition and the core premise of the instruction categories design. We propose a semi-automatic method for CFG construction with the help of Large-Language Models (LLMs). Then, we induct and generate data spanning five principal instruction categories (i.e. direction change, landmark recognition, region recognition, vertical movement, and numerical comprehension). Our analysis of different models reveals notable performance discrepancies and recurrent issues. The stagnation of numerical comprehension, heavy selective biases over directional concepts, and other interesting findings contribute to the development of future language-guided navigation systems.

Redundancy-Aware Camera Selection for Indoor Scene Neural Rendering

Novel view synthesis of indoor scenes can be achieved by capturing a monocular video sequence of the environment. However, redundant information caused by artificial movements in the input video data reduces the efficiency of scene modeling. In this work, we tackle this challenge from the perspective of camera selection. We begin by constructing a similarity matrix that incorporates both the spatial diversity of the cameras and the semantic variation of the images. Based on this matrix, we use the Intra-List Diversity (ILD) metric to assess camera redundancy, formulating the camera selection task as an optimization problem. Then we apply a diversity-based sampling algorithm to optimize the camera selection. We also develop a new dataset, IndoorTraj, which includes long and complex camera movements captured by humans in virtual indoor environments, closely mimicking real-world scenarios. Experimental results demonstrate that our strategy outperforms other approaches under time and memory constraints. Remarkably, our method achieves performance comparable to models trained on the full dataset, while using only an average of 15% of the frames and 75% of the allotted time.

Self-Learning for Personalized Keyword Spotting on Ultra-Low-Power Audio Sensors

This paper proposes a self-learning framework to incrementally train (fine-tune) a personalized Keyword Spotting (KWS) model after the deployment on ultra-low power smart audio sensors. We address the fundamental problem of the absence of labeled training data by assigning pseudo-labels to the new recorded audio frames based on a similarity score with respect to few user recordings. By experimenting with multiple KWS models with a number of parameters up to 0.5M on two public datasets, we show an accuracy improvement of up to +19.2% and +16.0% vs. the initial models pretrained on a large set of generic keywords. The labeling task is demonstrated on a sensor system composed of a low-power microphone and an energy-efficient Microcontroller (MCU). By efficiently exploiting the heterogeneous processing engines of the MCU, the always-on labeling task runs in real-time with an average power cost of up to 8.2 mW. On the same platform, we estimate an energy cost for on-device training 10x lower than the labeling energy if sampling a new utterance every 5 s or 16.4 s with a DS-CNN-S or a DS-CNN-M model. Our empirical result paves the way to self-adaptive personalized KWS sensors at the extreme edge.

Implicit Gaussian Splatting with Efficient Multi-Level Tri-Plane Representation

Recent advancements in photo-realistic novel view synthesis have been significantly driven by Gaussian Splatting (3DGS). Nevertheless, the explicit nature of 3DGS data entails considerable storage requirements, highlighting a pressing need for more efficient data representations. To address this, we present Implicit Gaussian Splatting (IGS), an innovative hybrid model that integrates explicit point clouds with implicit feature embeddings through a multi-level tri-plane architecture. This architecture features 2D feature grids at various resolutions across different levels, facilitating continuous spatial domain representation and enhancing spatial correlations among Gaussian primitives. Building upon this foundation, we introduce a level-based progressive training scheme, which incorporates explicit spatial regularization. This method capitalizes on spatial correlations to enhance both the rendering quality and the compactness of the IGS representation. Furthermore, we propose a novel compression pipeline tailored for both point clouds and 2D feature grids, considering the entropy variations across different levels. Extensive experimental evaluations demonstrate that our algorithm can deliver high-quality rendering using only a few MBs, effectively balancing storage efficiency and rendering fidelity, and yielding results that are competitive with the state-of-the-art.

Learning to Route for Dynamic Adapter Composition in Continual Learning with Language Models

Parameter-efficient fine-tuning (PEFT) methods are increasingly used with pre-trained language models (PLMs) for continual learning (CL). These methods involve training a PEFT module for each new task and using similarity-based selection to route modules during inference. However, they face two major limitations: 1) interference with already learned modules and 2) suboptimal routing when composing modules. In this paper, we introduce a method that isolates the training of PEFT modules for task specialization. Then, before evaluation, it learns to compose the previously learned modules by training a router that leverages samples from a small memory. We evaluate our method in two CL setups using several benchmarks. Our results show that our method provides a better composition of PEFT modules, leading to better generalization and performance compared to previous methods.

A Simple Framework for Open-Vocabulary Zero-Shot Segmentation

Zero-shot classification capabilities naturally arise in models trained within a vision-language contrastive framework. Despite their classification prowess, these models struggle in dense tasks like zero-shot open-vocabulary segmentation. This deficiency is often attributed to the absence of localization cues in captions and the intertwined nature of the learning process, which encompasses both image representation learning and cross-modality alignment. To tackle these issues, we propose SimZSS, a Simple framework for open-vocabulary Zero-Shot Segmentation. The method is founded on two key principles: i) leveraging frozen vision-only models that exhibit spatial awareness while exclusively aligning the text encoder and ii) exploiting the discrete nature of text and linguistic knowledge to pinpoint local concepts within captions. By capitalizing on the quality of the visual representations, our method requires only image-caption pairs datasets and adapts to both small curated and large-scale noisy datasets. When trained on COCO Captions across 8 GPUs, SimZSS achieves state-of-the-art results on 7 out of 8 benchmark datasets in less than 15 minutes.

Forgetting Order of Continual Learning: Examples That are Learned First are Forgotten Last

Catastrophic forgetting poses a significant challenge in continual learning, where models often forget previous tasks when trained on new data. Our empirical analysis reveals a strong correlation between catastrophic forgetting and the learning speed of examples: examples learned early are rarely forgotten, while those learned later are more susceptible to forgetting. We demonstrate that replay-based continual learning methods can leverage this phenomenon by focusing on mid-learned examples for rehearsal. We introduce Goldilocks, a novel replay buffer sampling method that filters out examples learned too quickly or too slowly, keeping those learned at an intermediate speed. Goldilocks improves existing continual learning algorithms, leading to state-of-the-art performance across several image classification tasks.