Visual Cue Enhancement and Dual Low-Rank Adaptation for Efficient Visual Instruction Fine-Tuning

Fine-tuning multimodal large language models (MLLMs) presents significant challenges, including a reliance on high-level visual features that limits fine-grained detail comprehension, and data conflicts that arise from task complexity. To address these issues, we propose an efficient fine-tuning framework with two novel approaches: Vision Cue Enhancement (VCE) and Dual Low-Rank Adaptation (Dual-LoRA). VCE enhances the vision projector by integrating multi-level visual cues, improving the model's ability to capture fine-grained visual features. Dual-LoRA introduces a dual low-rank structure for instruction tuning, decoupling learning into skill and task spaces to enable precise control and efficient adaptation across diverse tasks. Our method simplifies implementation, enhances visual comprehension, and improves adaptability. Experiments on both downstream tasks and general benchmarks demonstrate the effectiveness of our proposed approach.

Retrieval Augmented Recipe Generation

Given the potential applications of generating recipes from food images, this area has garnered significant attention from researchers in recent years. Existing works for recipe generation primarily utilize a two-stage training method, first generating ingredients and then obtaining instructions from both the image and ingredients. Large Multi-modal Models (LMMs), which have achieved notable success across a variety of vision and language tasks, shed light to generating both ingredients and instructions directly from images. Nevertheless, LMMs still face the common issue of hallucinations during recipe generation, leading to suboptimal performance. To tackle this, we propose a retrieval augmented large multimodal model for recipe generation. We first introduce Stochastic Diversified Retrieval Augmentation (SDRA) to retrieve recipes semantically related to the image from an existing datastore as a supplement, integrating them into the prompt to add diverse and rich context to the input image. Additionally, Self-Consistency Ensemble Voting mechanism is proposed to determine the most confident prediction recipes as the final output. It calculates the consistency among generated recipe candidates, which use different retrieval recipes as context for generation. Extensive experiments validate the effectiveness of our proposed method, which demonstrates state-of-the-art (SOTA) performance in recipe generation tasks on the Recipe1M dataset.

WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines

Vision Language Models (VLMs) often struggle with culture-specific knowledge, particularly in languages other than English and in underrepresented cultural contexts. To evaluate their understanding of such knowledge, we introduce WorldCuisines, a massive-scale benchmark for multilingual and multicultural, visually grounded language understanding. This benchmark includes a visual question answering (VQA) dataset with text-image pairs across 30 languages and dialects, spanning 9 language families and featuring over 1 million data points, making it the largest multicultural VQA benchmark to date. It includes tasks for identifying dish names and their origins. We provide evaluation datasets in two sizes (12k and 60k instances) alongside a training dataset (1 million instances). Our findings show that while VLMs perform better with correct location context, they struggle with adversarial contexts and predicting specific regional cuisines and languages. To support future research, we release a knowledge base with annotated food entries and images along with the VQA data.

Hi3D: Pursuing High-Resolution Image-to-3D Generation with Video Diffusion Models

Despite having tremendous progress in image-to-3D generation, existing methods still struggle to produce multi-view consistent images with high-resolution textures in detail, especially in the paradigm of 2D diffusion that lacks 3D awareness. In this work, we present High-resolution Image-to-3D model (Hi3D), a new video diffusion based paradigm that redefines a single image to multi-view images as 3D-aware sequential image generation (i.e., orbital video generation). This methodology delves into the underlying temporal consistency knowledge in video diffusion model that generalizes well to geometry consistency across multiple views in 3D generation. Technically, Hi3D first empowers the pre-trained video diffusion model with 3D-aware prior (camera pose condition), yielding multi-view images with low-resolution texture details. A 3D-aware video-to-video refiner is learnt to further scale up the multi-view images with high-resolution texture details. Such high-resolution multi-view images are further augmented with novel views through 3D Gaussian Splatting, which are finally leveraged to obtain high-fidelity meshes via 3D reconstruction. Extensive experiments on both novel view synthesis and single view reconstruction demonstrate that our Hi3D manages to produce superior multi-view consistency images with highly-detailed textures. Source code and data are available at \url{https://github.com/yanghb22-fdu/Hi3D-Official}.

RoDE: Linear Rectified Mixture of Diverse Experts for Food Large Multi-Modal Models

Large Multi-modal Models (LMMs) have significantly advanced a variety of vision-language tasks. The scalability and availability of high-quality training data play a pivotal role in the success of LMMs. In the realm of food, while comprehensive food datasets such as Recipe1M offer an abundance of ingredient and recipe information, they often fall short of providing ample data for nutritional analysis. The Recipe1M+ dataset, despite offering a subset for nutritional evaluation, is limited in the scale and accuracy of nutrition information. To bridge this gap, we introduce Uni-Food, a unified food dataset that comprises over 100,000 images with various food labels, including categories, ingredients, recipes, and ingredient-level nutritional information. Uni-Food is designed to provide a more holistic approach to food data analysis, thereby enhancing the performance and capabilities of LMMs in this domain. To mitigate the conflicts arising from multi-task supervision during fine-tuning of LMMs, we introduce a novel Linear Rectification Mixture of Diverse Experts (RoDE) approach. RoDE utilizes a diverse array of experts to address tasks of varying complexity, thereby facilitating the coordination of trainable parameters, i.e., it allocates more parameters for more complex tasks and, conversely, fewer parameters for simpler tasks. RoDE implements linear rectification union to refine the router's functionality, thereby enhancing the efficiency of sparse task allocation. These design choices endow RoDE with features that ensure GPU memory efficiency and ease of optimization. Our experimental results validate the effectiveness of our proposed approach in addressing the inherent challenges of food-related multitasking.

PosMLP-Video: Spatial and Temporal Relative Position Encoding for Efficient Video Recognition

In recent years, vision Transformers and MLPs have demonstrated remarkable performance in image understanding tasks. However, their inherently dense computational operators, such as self-attention and token-mixing layers, pose significant challenges when applied to spatio-temporal video data. To address this gap, we propose PosMLP-Video, a lightweight yet powerful MLP-like backbone for video recognition. Instead of dense operators, we use efficient relative positional encoding (RPE) to build pairwise token relations, leveraging small-sized parameterized relative position biases to obtain each relation score. Specifically, to enable spatio-temporal modeling, we extend the image PosMLP's positional gating unit to temporal, spatial, and spatio-temporal variants, namely PoTGU, PoSGU, and PoSTGU, respectively. These gating units can be feasibly combined into three types of spatio-temporal factorized positional MLP blocks, which not only decrease model complexity but also maintain good performance. Additionally, we enrich relative positional relationships by using channel grouping. Experimental results on three video-related tasks demonstrate that PosMLP-Video achieves competitive speed-accuracy trade-offs compared to the previous state-of-the-art models. In particular, PosMLP-Video pre-trained on ImageNet1K achieves 59.0%/70.3% top-1 accuracy on Something-Something V1/V2 and 82.1% top-1 accuracy on Kinetics-400 while requiring much fewer parameters and FLOPs than other models. The code is released at https://github.com/zhouds1918/PosMLP_Video.

Improving Interpretable Embeddings for Ad-hoc Video Search with Generative Captions and Multi-word Concept Bank

Aligning a user query and video clips in cross-modal latent space and that with semantic concepts are two mainstream approaches for ad-hoc video search (AVS). However, the effectiveness of existing approaches is bottlenecked by the small sizes of available video-text datasets and the low quality of concept banks, which results in the failures of unseen queries and the out-of-vocabulary problem. This paper addresses these two problems by constructing a new dataset and developing a multi-word concept bank. Specifically, capitalizing on a generative model, we construct a new dataset consisting of 7 million generated text and video pairs for pre-training. To tackle the out-of-vocabulary problem, we develop a multi-word concept bank based on syntax analysis to enhance the capability of a state-of-the-art interpretable AVS method in modeling relationships between query words. We also study the impact of current advanced features on the method. Experimental results show that the integration of the above-proposed elements doubles the R@1 performance of the AVS method on the MSRVTT dataset and improves the xinfAP on the TRECVid AVS query sets for 2016-2023 (eight years) by a margin from 2% to 77%, with an average about 20%.

OVFoodSeg: Elevating Open-Vocabulary Food Image Segmentation via Image-Informed Textual Representation

In the realm of food computing, segmenting ingredients from images poses substantial challenges due to the large intra-class variance among the same ingredients, the emergence of new ingredients, and the high annotation costs associated with large food segmentation datasets. Existing approaches primarily utilize a closed-vocabulary and static text embeddings setting. These methods often fall short in effectively handling the ingredients, particularly new and diverse ones. In response to these limitations, we introduce OVFoodSeg, a framework that adopts an open-vocabulary setting and enhances text embeddings with visual context. By integrating vision-language models (VLMs), our approach enriches text embedding with image-specific information through two innovative modules, eg, an image-to-text learner FoodLearner and an Image-Informed Text Encoder. The training process of OVFoodSeg is divided into two stages: the pre-training of FoodLearner and the subsequent learning phase for segmentation. The pre-training phase equips FoodLearner with the capability to align visual information with corresponding textual representations that are specifically related to food, while the second phase adapts both the FoodLearner and the Image-Informed Text Encoder for the segmentation task. By addressing the deficiencies of previous models, OVFoodSeg demonstrates a significant improvement, achieving an 4.9\% increase in mean Intersection over Union (mIoU) on the FoodSeg103 dataset, setting a new milestone for food image segmentation.

Interpretable Embedding for Ad-hoc Video Search

Answering query with semantic concepts has long been the mainstream approach for video search. Until recently, its performance is surpassed by concept-free approach, which embeds queries in a joint space as videos. Nevertheless, the embedded features as well as search results are not interpretable, hindering subsequent steps in video browsing and query reformulation. This paper integrates feature embedding and concept interpretation into a neural network for unified dual-task learning. In this way, an embedding is associated with a list of semantic concepts as an interpretation of video content. This paper empirically demonstrates that, by using either the embedding features or concepts, considerable search improvement is attainable on TRECVid benchmarked datasets. Concepts are not only effective in pruning false positive videos, but also highly complementary to concept-free search, leading to large margin of improvement compared to state-of-the-art approaches.

FoodLMM: A Versatile Food Assistant using Large Multi-modal Model

Large Multi-modal Models (LMMs) have made impressive progress in many vision-language tasks. Nevertheless, the performance of general LMMs in specific domains is still far from satisfactory. This paper proposes FoodLMM, a versatile food assistant based on LMMs with various capabilities, including food recognition, ingredient recognition, recipe generation, nutrition estimation, food segmentation and multi-round conversation. To facilitate FoodLMM to deal with tasks beyond pure text output, we introduce a series of novel task-specific tokens and heads, enabling the model to predict food nutritional values and multiple segmentation masks. We adopt a two-stage training strategy. In the first stage, we utilize multiple public food benchmarks for multi-task learning by leveraging instruct-following paradigm. In the second stage, we construct a multi-round conversation and a reasoning segmentation datasets to fine-tune the model, enabling it to conduct professional dialogues and generate segmentation masks based on complex reasoning in food domain. Our fine-tuned FoodLMM achieves state-of-the-art results across several food benchmarks. We will make our code, models and datasets publicly available.