pith. sign in

arxiv: 1902.09506 · v3 · pith:H3OHMD7Gnew · submitted 2019-02-25 · 💻 cs.CL · cs.AI· cs.CV· cs.LG

GQA: A New Dataset for Real-World Visual Reasoning and Compositional Question Answering

classification 💻 cs.CL cs.AIcs.CVcs.LG
keywords questiondatasetmodelsreasoningansweringcompositionalconsistencyprograms
0
0 comments X
read the original abstract

We introduce GQA, a new dataset for real-world visual reasoning and compositional question answering, seeking to address key shortcomings of previous VQA datasets. We have developed a strong and robust question engine that leverages scene graph structures to create 22M diverse reasoning questions, all come with functional programs that represent their semantics. We use the programs to gain tight control over the answer distribution and present a new tunable smoothing technique to mitigate question biases. Accompanying the dataset is a suite of new metrics that evaluate essential qualities such as consistency, grounding and plausibility. An extensive analysis is performed for baselines as well as state-of-the-art models, providing fine-grained results for different question types and topologies. Whereas a blind LSTM obtains mere 42.1%, and strong VQA models achieve 54.1%, human performance tops at 89.3%, offering ample opportunity for new research to explore. We strongly hope GQA will provide an enabling resource for the next generation of models with enhanced robustness, improved consistency, and deeper semantic understanding for images and language.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 18 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. PluRule: A Benchmark for Moderating Pluralistic Communities on Social Media

    cs.CL 2026-05 unverdicted novelty 7.0

    PluRule is a new multimodal multilingual benchmark showing that state-of-the-art vision-language models perform only marginally better than a trivial baseline at detecting specific rule violations in pluralistic onlin...

  2. V-RoAst: Visual Road Assessment. Can VLM be a Road Safety Assessor Using the iRAP Standard?

    cs.CV 2024-08 unverdicted novelty 7.0

    V-RoAst applies zero-shot VLMs (Gemini-1.5-flash, GPT-4o-mini) to iRAP road safety attribute classification on a new ThaiRAP image dataset and compares them to CNN baselines, finding better generalization to unseen cl...

  3. ViperGPT: Visual Inference via Python Execution for Reasoning

    cs.CV 2023-03 unverdicted novelty 7.0

    ViperGPT generates executable Python code to compose pre-trained vision-and-language modules into programs that answer visual queries, reaching state-of-the-art results with no additional training.

  4. SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference

    cs.LG 2026-06 unverdicted novelty 6.0

    SharQ combines input-adaptive N:M sparsity and FP4 quantization via sparse backbone plus dense residual, recovering 43-63% of the NVFP4-to-FP16 accuracy gap on Llama and Qwen models without calibration or retraining.

  5. VTOS: Learning to Orchestrate Vision Tools by Co-Searching Solutions and Observers

    cs.CV 2026-06 unverdicted novelty 6.0

    VTOS jointly searches solution and observer programs to adaptively orchestrate vision tools, outperforming static pipelines on dense object counting and zero-shot plant disease segmentation.

  6. IDEAL: In-DEpth ALignment Makes A Discrete Representation AutoEncoder

    cs.CV 2026-06 unverdicted novelty 6.0

    IDEAL improves discrete representation autoencoders by jointly aligning quantized tokens with shallow and deep VFM features, reporting 0.61 rFID on ImageNet and 1.89 gFID for autoregressive image generation.

  7. When Attention Collapses: Stage-Aware Visual Token Pruning from Structure to Semantics

    cs.CV 2026-06 unverdicted novelty 6.0

    STS is a two-stage pruning framework that decouples structural diversity via repulsion sampling from semantic filtering via cross-attention to reduce redundancy in visual tokens for VLMs.

  8. PGT: Procedurally Generated Tasks for improving visual grounding in MLLMs

    cs.CV 2026-05 unverdicted novelty 6.0

    PGT generates synthetic tasks via geometric overlays on images to supply dense visual supervision, improving spatial and relational understanding in MLLMs by up to 20% on targeted benchmarks.

  9. From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models

    cs.CL 2026-05 conditional novelty 6.0

    Staged post-training that first solidifies visual perception before visual and textual reasoning improves VLM accuracy and shortens reasoning traces on visual math and perception benchmarks.

  10. ProEval: Proactive Failure Discovery and Efficient Performance Estimation for Generative AI Evaluation

    cs.LG 2026-04 unverdicted novelty 6.0

    ProEval is a proactive framework using pre-trained GPs, Bayesian quadrature, and superlevel set sampling to estimate performance and find failures in generative AI with 8-65x fewer samples than baselines.

  11. ProEval: Proactive Failure Discovery and Efficient Performance Estimation for Generative AI Evaluation

    cs.LG 2026-04 conditional novelty 6.0

    Bayesian deep learning method rankings are unreliable under data scarcity, reversing across datasets and sample sizes, and a hierarchical Bayesian framework with predictive detectability curves is needed to assess eva...

  12. Fourier Compressor: Frequency-Domain Visual Token Compression for Vision-Language Models

    cs.CV 2025-08 unverdicted novelty 6.0

    Fourier Compressor uses FFT to remove frequency-domain redundancy from visual tokens in VLMs, retaining over 96% accuracy with up to 83.8% FLOP reduction.

  13. RTP-LLM: High-Performance Alibaba LLM Inference Engine

    cs.OS 2026-05 unverdicted novelty 5.0

    RTP-LLM is a new LLM inference engine achieving 4.7x-6.3x model loading speedup and 1.12x-2.52x throughput gains over vLLM and SGLang via disaggregated phases, multi-tier KV cache, and modular optimizations in product...

  14. MIRAGE: A Micro-Interaction Relational Architecture for Grounded Exploration in Multi-Figure Artworks

    cs.CV 2026-04 unverdicted novelty 5.0

    MIRAGE improves VLM analysis of multi-figure art by inserting a verifiable structured representation of micro-interactions between spatial grounding and narrative output.

  15. AutoVQA-G: Self-Improving Agentic Framework for Automated Visual Question Answering and Grounding Annotation

    cs.CV 2026-04 unverdicted novelty 5.0

    AutoVQA-G is a self-improving framework that generates VQA-G datasets with higher visual grounding accuracy than leading multimodal LLMs via iterative CoT verification and prompt refinement.

  16. CoGR-MoE: Concept-Guided Expert Routing with Consistent Selection and Flexible Reasoning for Visual Question Answering

    cs.CV 2026-04 unverdicted novelty 5.0

    CoGR-MoE improves VQA by using concept-guided expert routing with option feature reweighting and contrastive learning to achieve consistent yet flexible reasoning across answer options.

  17. Preserving Knowledge in Large Language Model with Model-Agnostic Self-Decompression

    cs.CL 2024-06 unverdicted novelty 5.0

    Introduces Tree Generation (TG-SFT) to generate synthetic instruction-tuning data from LLMs, reducing catastrophic forgetting when fine-tuning MLLMs on domain-specific or multimodal data.

  18. PaliGemma: A versatile 3B VLM for transfer

    cs.CV 2024-07 unverdicted novelty 4.0

    PaliGemma is an open 3B VLM based on SigLIP and Gemma that achieves strong performance on nearly 40 diverse open-world tasks including benchmarks, remote-sensing, and segmentation.