Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach

Self-improvement in multimodal large language models (MLLMs) is crucial for enhancing their reliability and robustness. However, current methods often rely heavily on MLLMs themselves as judges, leading to high computational costs and potential pitfalls like reward hacking and model collapse. This paper introduces a novel, model-level judge-free self-improvement framework. Our approach employs a controlled feedback mechanism while eliminating the need for MLLMs in the verification loop. We generate preference learning pairs using a controllable hallucination mechanism and optimize data quality by leveraging lightweight, contrastive language-image encoders to evaluate and reverse pairs when necessary. Evaluations across public benchmarks and our newly introduced IC dataset designed to challenge hallucination control demonstrate that our model outperforms conventional techniques. We achieve superior precision and recall with significantly lower computational demands. This method offers an efficient pathway to scalable self-improvement in MLLMs, balancing performance gains with reduced resource requirements.

Quadratic Is Not What You Need For Multimodal Large Language Models

In the past year, the capabilities of Multimodal Large Language Models (MLLMs) have significantly improved across various aspects. However, constrained by the quadratic growth of computation in LLMs as the number of tokens increases, efficiency has become a bottleneck for further scaling MLLMs. Although recent efforts have been made to prune visual tokens or use more lightweight LLMs to reduce computation, the problem of quadratic growth in computation with the increase of visual tokens still persists. To address this, we propose a novel approach: instead of reducing the input visual tokens for LLMs, we focus on pruning vision-related computations within the LLMs. After pruning, the computation growth in the LLM is no longer quadratic with the increase of visual tokens, but linear. Surprisingly, we found that after applying such extensive pruning, the capabilities of MLLMs are comparable with the original one and even superior on some benchmarks with only 25% of the computation. This finding opens up the possibility for MLLMs to incorporate much denser visual tokens. Additionally, based on this finding, we further analyzed some architectural design deficiencies in existing MLLMs and proposed promising improvements. To the best of our knowledge, this is the first study to investigate the computational redundancy in the LLM's vision component of MLLMs. Code and checkpoints will be released soon.

DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision

We have witnessed significant progress in deep learning-based 3D vision, ranging from neural radiance field (NeRF) based 3D representation learning to applications in novel view synthesis (NVS). However, existing scene-level datasets for deep learning-based 3D vision, limited to either synthetic environments or a narrow selection of real-world scenes, are quite insufficient. This insufficiency not only hinders a comprehensive benchmark of existing methods but also caps what could be explored in deep learning-based 3D analysis. To address this critical gap, we present DL3DV-10K, a large-scale scene dataset, featuring 51.2 million frames from 10,510 videos captured from 65 types of point-of-interest (POI) locations, covering both bounded and unbounded scenes, with different levels of reflection, transparency, and lighting. We conducted a comprehensive benchmark of recent NVS methods on DL3DV-10K, which revealed valuable insights for future research in NVS. In addition, we have obtained encouraging results in a pilot study to learn generalizable NeRF from DL3DV-10K, which manifests the necessity of a large-scale scene-level dataset to forge a path toward a foundation model for learning 3D representation. Our DL3DV-10K dataset, benchmark results, and models will be publicly accessible at https://dl3dv-10k.github.io/DL3DV-10K/.

Text2Layer: Layered Image Generation using Latent Diffusion Model

Layer compositing is one of the most popular image editing workflows among both amateurs and professionals. Motivated by the success of diffusion models, we explore layer compositing from a layered image generation perspective. Instead of generating an image, we propose to generate background, foreground, layer mask, and the composed image simultaneously. To achieve layered image generation, we train an autoencoder that is able to reconstruct layered images and train diffusion models on the latent representation. One benefit of the proposed problem is to enable better compositing workflows in addition to the high-quality image output. Another benefit is producing higher-quality layer masks compared to masks produced by a separate step of image segmentation. Experimental results show that the proposed method is able to generate high-quality layered images and initiates a benchmark for future work.

Boosting Entity-aware Image Captioning with Multi-modal Knowledge Graph

Entity-aware image captioning aims to describe named entities and events related to the image by utilizing the background knowledge in the associated article. This task remains challenging as it is difficult to learn the association between named entities and visual cues due to the long-tail distribution of named entities. Furthermore, the complexity of the article brings difficulty in extracting fine-grained relationships between entities to generate informative event descriptions about the image. To tackle these challenges, we propose a novel approach that constructs a multi-modal knowledge graph to associate the visual objects with named entities and capture the relationship between entities simultaneously with the help of external knowledge collected from the web. Specifically, we build a text sub-graph by extracting named entities and their relationships from the article, and build an image sub-graph by detecting the objects in the image. To connect these two sub-graphs, we propose a cross-modal entity matching module trained using a knowledge base that contains Wikipedia entries and the corresponding images. Finally, the multi-modal knowledge graph is integrated into the captioning model via a graph attention mechanism. Extensive experiments on both GoodNews and NYTimes800k datasets demonstrate the effectiveness of our method.

Video Question Answering on Screencast Tutorials

This paper presents a new video question answering task on screencast tutorials. We introduce a dataset including question, answer and context triples from the tutorial videos for a software. Unlike other video question answering works, all the answers in our dataset are grounded to the domain knowledge base. An one-shot recognition algorithm is designed to extract the visual cues, which helps enhance the performance of video question answering. We also propose several baseline neural network architectures based on various aspects of video contexts from the dataset. The experimental results demonstrate that our proposed models significantly improve the question answering performances by incorporating multi-modal contexts and domain knowledge.

Weakly Supervised Object Localization with Inter-Intra Regulated CAMs

Weakly supervised object localization (WSOL) aims to locate objects in images by learning only from image-level labels. Current methods are trying to obtain localization results relying on Class Activation Maps (CAMs). Usually, they propose additional CAMs or feature maps generated from internal layers of deep networks to encourage different CAMs to be either \textbf{adversarial} or \textbf{cooperated} with each other. In this work, instead of following one of the two main approaches before, we analyze their internal relationship and propose a novel intra-sample strategy which regulates two CAMs of the same sample, generated from different classifiers, to dynamically adapt each of their pixels involved in adversarial or cooperative process based on their own values. We mathematically demonstrate that our approach is a more general version of the current state-of-the-art method with less hyper-parameters. Besides, we further develop an inter-sample criterion module for our WSOL task, which is originally proposed in co-segmentation problems, to refine generated CAMs of each sample. The module considers a subgroup of samples under the same category and regulates their object regions. With experiment on two widely-used datasets, we show that our proposed method significantly outperforms existing state-of-the-art, setting a new record for weakly-supervised object localization.

Weakly Supervised Localization Using Background Images

Weakly Supervised Object Localization (WSOL) methodsusually rely on fully convolutional networks in order to ob-tain class activation maps(CAMs) of targeted labels. How-ever, these networks always highlight the most discriminativeparts to perform the task, the located areas are much smallerthan entire targeted objects. In this work, we propose a novelend-to-end model to enlarge CAMs generated from classifi-cation models, which can localize targeted objects more pre-cisely. In detail, we add an additional module in traditionalclassification networks to extract foreground object propos-als from images without classifying them into specific cate-gories. Then we set these normalized regions as unrestrictedpixel-level mask supervision for the following classificationtask. We collect a set of images defined as Background ImageSet from the Internet. The number of them is much smallerthan the targeted dataset but surprisingly well supports themethod to extract foreground regions from different pictures.The region extracted is independent from classification task,where the extracted region in each image covers almost en-tire object rather than just a significant part. Therefore, theseregions can serve as masks to supervise the response mapgenerated from classification models to become larger andmore precise. The method achieves state-of-the-art results onCUB-200-2011 in terms of Top-1 and Top-5 localization er-ror while has a competitive result on ILSVRC2016 comparedwith other approaches.

Relational Reasoning using Prior Knowledge for Visual Captioning

Exploiting relationships among objects has achieved remarkable progress in interpreting images or videos by natural language. Most existing methods resort to first detecting objects and their relationships, and then generating textual descriptions, which heavily depends on pre-trained detectors and leads to performance drop when facing problems of heavy occlusion, tiny-size objects and long-tail in object detection. In addition, the separate procedure of detecting and captioning results in semantic inconsistency between the pre-defined object/relation categories and the target lexical words. We exploit prior human commonsense knowledge for reasoning relationships between objects without any pre-trained detectors and reaching semantic coherency within one image or video in captioning. The prior knowledge (e.g., in the form of knowledge graph) provides commonsense semantic correlation and constraint between objects that are not explicit in the image and video, serving as useful guidance to build semantic graph for sentence generation. Particularly, we present a joint reasoning method that incorporates 1) commonsense reasoning for embedding image or video regions into semantic space to build semantic graph and 2) relational reasoning for encoding semantic graph to generate sentences. Extensive experiments on the MS-COCO image captioning benchmark and the MSVD video captioning benchmark validate the superiority of our method on leveraging prior commonsense knowledge to enhance relational reasoning for visual captioning.

How to Make a BLT Sandwich? Learning to Reason towards Understanding Web Instructional Videos

Understanding web instructional videos is an essential branch of video understanding in two aspects. First, most existing video methods focus on short-term actions for a-few-second-long video clips; these methods are not directly applicable to long videos. Second, unlike unconstrained long videos, e.g., movies, instructional videos are more structured in that they have step-by-step procedure constraining the understanding task. In this paper, we study reasoning on instructional videos via question-answering (QA). Surprisingly, it has not been an emphasis in the video community despite its rich applications. We thereby introduce YouQuek, an annotated QA dataset for instructional videos based on the recent YouCook2. The questions in YouQuek are not limited to cues on one frame but related to logical reasoning in the temporal dimension. Observing the lack of effective representations for modeling long videos, we propose a set of carefully designed models including a novel Recurrent Graph Convolutional Network (RGCN) that captures both temporal order and relation information. Furthermore, we study multiple modalities including description and transcripts for the purpose of boosting video understanding. Extensive experiments on YouQuek suggest that RGCN performs the best in terms of QA accuracy and a better performance is gained by introducing human annotated description.