A Note on the Inception Score
read the original abstract
Deep generative models are powerful tools that have produced impressive results in recent years. These advances have been for the most part empirically driven, making it essential that we use high quality evaluation metrics. In this paper, we provide new insights into the Inception Score, a recently proposed and widely used evaluation metric for generative models, and demonstrate that it fails to provide useful guidance when comparing models. We discuss both suboptimalities of the metric itself and issues with its application. Finally, we call for researchers to be more systematic and careful when evaluating and comparing generative models, as the advancement of the field depends upon it.
This paper has not been read by Pith yet.
Forward citations
Cited by 14 Pith papers
-
OccDirector: Language-Guided Behavior and Interaction Generation in 4D Occupancy Space
OccDirector uses a VLM-guided Spatio-Temporal MMDiT model with history anchoring to generate physically plausible 4D occupancy from language scripts, supported by the new OccInteract-85k dataset.
-
Diffusion Models Beat GANs on Image Synthesis
Diffusion models with architecture improvements and classifier guidance achieve superior FID scores to GANs on unconditional and conditional ImageNet image synthesis.
-
Large Scale GAN Training for High Fidelity Natural Image Synthesis
BigGANs achieve state-of-the-art class-conditional synthesis on ImageNet 128x128 with Inception Score 166.5 and FID 7.4 by scaling GANs and applying orthogonal regularization plus truncation.
-
Optimizing Visual Generative Models via Distribution-wise Rewards
Distribution-wise rewards with subset-replace strategy and post-hoc merging improve FID-50K on SiT (8.30 to 5.77) and EDM2 (3.74 to 3.52) while preserving diversity.
-
Post-Training Pruning for Diffusion Transformers
DiT-Pruning introduces an energy-based saliency metric balancing weights and activations plus clustering-aware granularity for post-training pruning of DiTs, showing near-zero CLIP score degradation at 50% sparsity on...
-
Diffusion Fine-tuning with Rewarded Moment Matching Distillation
RMMD simultaneously distills diffusion models and optimizes rewards, yielding better FID-reward trade-offs on ImageNet than DI++, DRaFT and HyperNoise, and a 7.5x faster GenCast model that beats its teacher on 93% of ...
-
The FID Lottery: Quantifying Hidden Randomness in Generative-Model Evaluation
FID variance from training seeds is 3.2 times larger than from sampling seeds on hundreds of SiT models, with 1-2% coefficient of variation that barely shrinks with more compute, leading to a multi-seed evaluation protocol.
-
UAT: Unified Audio-Text Diffusion for Audio Generation, Editing, and Captioning
UAT presents a diffusion-centric framework coupling continuous latent diffusion for audio with masked discrete diffusion for text in a shared dual-stream backbone to enable unified generation, editing, and captioning.
-
Generative Recursive Reasoning
GRAM turns recursive latent reasoning into a generative probabilistic model via stochastic trajectories and amortized variational inference, claiming better performance on structured reasoning tasks than deterministic...
-
Generative Recursive Reasoning
GRAM is a latent-variable generative model that performs recursive reasoning via stochastic trajectories, trained with amortized variational inference to support multi-hypothesis reasoning and unconditional generation.
-
TC-AE: Unlocking Token Capacity for Deep Compression Autoencoders
TC-AE improves reconstruction and generative performance in deep compression by decomposing token-to-latent compression into two stages and using joint self-supervised training.
-
Speculative Coupled Decoding for Training-Free Lossless Acceleration of Autoregressive Visual Generation
Speculative Coupled Decoding stabilizes draft sampling in Speculative Jacobi Decoding via an information-theoretic coupling step, delivering up to 4.2x image and 13.6x video speedups with no quality loss or training.
-
Movie Gen: A Cast of Media Foundation Models
A 30B-parameter transformer and related models generate high-quality videos and audio, claiming state-of-the-art results on text-to-video, video editing, personalization, and audio generation tasks.
-
Image-to-Video Diffusion: From Foundations to Open Frontiers
A survey that organizes diffusion image-to-video methods into a taxonomy, distills core designs in condition encoding, temporal modeling, noise prior, and upsampling, and discusses applications plus challenges.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.